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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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 Local
    5. 6-RES_SCL-AJT
    6. 4942
    Prev
    Next
    INDEX
    Explanations

    words related to sudden, surprising, or intense emotional reactions, especially shock, distress, or surprise

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    +0.16
    0.7%
    447
    +0.16
    0.6%
    203
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.16
    -0.06
    718
    +0.16
    0.13
    374
    +0.15
    0.05
    Negative Logits
    uties
    -0.88
    amins
    -0.88
    allery
    -0.87
    ittees
    -0.77
     misunder
    -0.77
    umbers
    -0.75
     arrang
    -0.75
    guyen
    -0.75
    ately
    -0.73
     ledger
    -0.73
    POSITIVE LOGITS
    wave
    1.40
    waves
    1.35
     absor
    1.18
    tro
    1.06
    ingly
    1.02
    imaru
    0.96
    mong
    0.94
    crow
    0.94
    er
    0.91
    shock
    0.90
    Activations Density 8.817%

    No Known Activations