© 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. 1729
    Prev
    Next
    INDEX
    Explanations

    text related to software projects and development

    oai_token-act-pair · gpt-3.5-turbo
    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
    427
    +0.17
    0.6%
    301
    +0.14
    0.5%
    47
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    388
    +0.17
    0.09
    74
    +0.14
    0.08
    464
    +0.14
    0.08
    Negative Logits
    utsche
    -0.96
    tsky
    -0.93
    heit
    -0.91
     Verge
    -0.86
     overpower
    -0.85
    nir
    -0.84
     revol
    -0.84
    auga
    -0.84
    tein
    -0.83
    brook
    -0.82
    POSITIVE LOGITS
    ciation
    1.07
     guiActiveUnfocused
    0.96
     chaired
    0.96
    rors
    0.96
    ixt
    0.93
    viation
    0.87
    lation
    0.86
    ements
    0.86
    ATURE
    0.85
    packed
    0.85
    Activations Density 4.110%

    No Known Activations