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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5519
    Prev
    Next
    INDEX
    Explanations

    references to past achievements and experience, particularly in the context of a track record

    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
    288
    +0.18
    0.6%
    195
    +0.14
    0.5%
    249
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.18
    0.09
    288
    +0.14
    0.10
    195
    +0.13
    0.02
    Negative Logits
    hap
    -1.14
    abad
    -1.03
    imates
    -0.96
    tein
    -0.95
    ateurs
    -0.92
    adin
    -0.92
    wered
    -0.91
    imation
    -0.91
    tan
    -0.89
    utterstock
    -0.88
    POSITIVE LOGITS
     Incarn
    0.97
     record
    0.96
    ebin
    0.93
     histories
    0.91
     breaker
    0.89
     revolving
    0.89
     associ
    0.87
    record
    0.86
    Versions
    0.86
     dating
    0.83
    Activations Density 1.468%

    No Known Activations