© 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. 1329
    Prev
    Next
    INDEX
    Explanations

    phrases related to traumatic or distressing events and incidents

    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
    373
    +0.16
    0.7%
    159
    +0.15
    0.6%
    447
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.16
    0.05
    70
    +0.15
    0.05
    97
    +0.13
    0.03
    Negative Logits
    ylum
    -0.69
    ITY
    -0.64
    itic
    -0.64
    antha
    -0.63
     Tsukuyomi
    -0.63
     arresting
    -0.62
    arta
    -0.61
    terday
    -0.61
    aleigh
    -0.61
    archment
    -0.60
    POSITIVE LOGITS
    vous
    0.91
    eer
    0.83
    mitted
    0.79
     Frenzy
    0.69
    ouble
    0.66
    DON
    0.66
    ezvous
    0.65
    rodu
    0.65
    amn
    0.65
    eering
    0.65
    Activations Density 0.628%

    No Known Activations