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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 503
    Prev
    Next
    INDEX
    Explanations

    updates or new information in a document

    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
    274
    +0.19
    0.7%
    311
    +0.16
    0.6%
    195
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    140
    +0.19
    0.04
    274
    +0.16
    0.04
    195
    +0.15
    0.02
    Negative Logits
    aden
    -1.03
    athered
    -0.95
    ongh
    -0.94
    egu
    -0.94
    ung
    -0.94
    enic
    -0.93
    sembly
    -0.91
    ffiti
    -0.90
    è£
    -0.90
    stood
    -0.89
    POSITIVE LOGITS
    :]
    1.31
    UPDATE
    1.11
     EDIT
    1.06
     Update
    1.06
    Update
    1.03
     Corrections
    1.02
    INGTON
    1.01
     UPDATE
    1.00
    Meta
    1.00
    !]
    1.00
    Activations Density 0.385%

    No Known Activations