© 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. 3865
    Prev
    Next
    INDEX
    Explanations

    words related to negative emotions and feelings

    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
    608
    +0.14
    0.5%
    61
    +0.13
    0.5%
    496
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.14
    0.10
    507
    +0.13
    0.10
    61
    +0.12
    0.08
    Negative Logits
    ItemImage
    -1.08
    estone
    -1.07
    aqu
    -1.01
    ramid
    -1.00
    ammy
    -0.95
    DragonMagazine
    -0.94
    aunder
    -0.93
    aez
    -0.92
    essing
    -0.90
    ItemThumbnailImage
    -0.87
    POSITIVE LOGITS
     passionately
    1.06
    lessly
    1.04
    fully
    1.00
     dearly
    0.89
    ¿½
    0.87
     Enemy
    0.83
    ably
    0.83
     feelings
    0.82
     seeing
    0.80
     them
    0.80
    Activations Density 1.840%

    No Known Activations