© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 5404
    Prev
    Next
    INDEX
    Explanations

    text related to technology and software development environments

    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
    515
    +0.10
    0.5%
    258
    +0.09
    0.5%
    308
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    20
    +0.10
    0.01
    6
    +0.09
    0.01
    578
    +0.08
    0.01
    Negative Logits
    <?
    -0.66
    colo
    -0.63
    eryl
    -0.60
     MacArthur
    -0.60
    thood
    -0.60
    phrine
    -0.58
    aunder
    -0.57
    IZE
    -0.56
    é¾įå¥ij士
    -0.56
    ause
    -0.55
    POSITIVE LOGITS
    join
    0.62
     Dag
    0.61
     tru
    0.57
    atom
    0.56
    grown
    0.56
    kn
    0.54
    christ
    0.54
     Tags
    0.53
    yna
    0.52
     ali
    0.52
    Activations Density 0.007%

    No Known Activations