Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34157
    Prev
    Next
    INDEX
    Explanations

    keywords related to audio and sound

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    385
    +0.13
    0.6%
    578
    +0.12
    0.6%
    128
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.13
    0.07
    649
    +0.12
    0.03
    232
    +0.11
    0.07
    Negative Logits
    pent
    -0.70
     pall
    -0.68
    20439
    -0.64
    icably
    -0.63
    ONT
    -0.61
    onement
    -0.60
     visitation
    -0.60
     poppy
    -0.59
    perty
    -0.59
    315
    -0.58
    POSITIVE LOGITS
    track
    1.31
    wave
    0.91
    tracks
    0.80
    Cloud
    0.78
     Blaster
    0.77
     Instrument
    0.76
    song
    0.72
    Boost
    0.71
    system
    0.71
    Works
    0.71
    Activations Density 6.453%

    No Known Activations