© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 5661
    Prev
    Next
    INDEX
    Explanations

    references to sounds or noises

    oai_token-act-pair · gpt-3.5-turbo

    The "sound of" or the "smell of" something, especially activating around the "of" token

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    347
    +0.13
    0.7%
    543
    +0.12
    0.6%
    387
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.05
    593
    +0.12
    0.04
    172
    +0.11
    0.05
    Negative Logits
    ħĭ
    -0.71
    volent
    -0.69
    RGB
    -0.68
    iphany
    -0.64
    uristic
    -0.63
    alan
    -0.63
     pose
    -0.63
    ETF
    -0.61
    otype
    -0.59
    ibling
    -0.59
    POSITIVE LOGITS
     drums
    0.66
     instruments
    0.60
     bells
    0.60
     vibrations
    0.60
     whist
    0.58
     reverber
    0.56
     Orchestra
    0.56
    waves
    0.56
     gunshots
    0.56
     Equipment
    0.56
    Activations Density 0.532%

    No Known Activations