© 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. 5478
    Prev
    Next
    INDEX
    Explanations

    action sequences or narratives involving various characters in different settings

    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
    267
    +0.14
    0.5%
    727
    +0.13
    0.4%
    59
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.14
    0.13
    119
    +0.13
    0.10
    2
    +0.12
    0.06
    Negative Logits
     ..."
    -1.14
     âĢ¦"
    -0.85
     [|
    -0.85
     thereof
    -0.79
    "],"
    -0.77
    Ïī
    -0.77
    ��
    -0.75
    ..."
    -0.73
     srfAttach
    -0.73
    س
    -0.72
    POSITIVE LOGITS
    resa
    1.75
    odore
    1.59
    zbollah
    1.53
    pherd
    1.35
    xiety
    1.32
    anmar
    1.23
    miah
    1.22
    bidden
    1.17
    ldon
    1.13
    tymology
    1.11
    Activations Density 1.771%

    No Known Activations