© 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. 32086
    Prev
    Next
    INDEX
    Explanations

    words related to classification and categorization

    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
    +0.17
    0.8%
    161
    +0.10
    0.5%
    642
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.17
    0.10
    301
    +0.10
    0.08
    642
    +0.10
    0.03
    Negative Logits
     contrace
    -0.65
    zens
    -0.63
     entreprene
    -0.62
     awaken
    -0.62
    INTER
    -0.59
     enthusi
    -0.59
     abdom
    -0.59
     absor
    -0.59
    irc
    -0.58
     fundraiser
    -0.58
    POSITIVE LOGITS
    enance
    1.05
    ifications
    0.87
     distinctions
    0.80
    inctions
    0.79
    wana
    0.77
    eters
    0.69
     labels
    0.68
    ifies
    0.67
    anguage
    0.66
    ifiable
    0.66
    Activations Density 7.976%

    No Known Activations