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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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 Local
    9. 6-RES_SCL-AJT
    11. 35613
    Prev
    Next
    INDEX
    Explanations

    emotional and expressive phrases, including expletives and insults

    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
    +0.12
    0.6%
    326
    +0.10
    0.5%
    52
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.32
    580
    +0.10
    0.12
    55
    +0.09
    0.16
    Negative Logits
    oling
    -0.65
     Gaul
    -0.63
    isc
    -0.61
    amping
    -0.56
    itan
    -0.56
    ken
    -0.56
    vertisement
    -0.55
    ische
    -0.55
    Bloom
    -0.55
    ulatory
    -0.54
    POSITIVE LOGITS
    lihood
    1.10
    theless
    1.06
    terday
    0.93
    forth
    0.82
    soever
    0.80
    LY
    0.76
    selves
    0.74
    NESS
    0.73
    entimes
    0.73
    LECT
    0.73
    Activations Density 16.304%

    No Known Activations