© 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. 39439
    Prev
    Next
    INDEX
    Explanations

    actions and descriptions of characters' actions and emotions in a narrative context

    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
    447
    +0.36
    1.8%
    393
    +0.20
    1.0%
    178
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.36
    0.19
    546
    +0.20
    0.20
    297
    +0.12
    0.16
    Negative Logits
    ©
    -0.71
    isi
    -0.71
    UF
    -0.70
    uitive
    -0.67
    ¤
    -0.64
    pec
    -0.64
    inic
    -0.64
    ocl
    -0.62
    irie
    -0.62
    yon
    -0.61
    POSITIVE LOGITS
     albeit
    1.09
     prompting
    0.95
     although
    0.90
     leaving
    0.90
     lest
    0.87
     letting
    0.86
     grinning
    0.86
     allowing
    0.85
     but
    0.85
     indicating
    0.85
    Activations Density 9.648%

    No Known Activations