© 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. 35899
    Prev
    Next
    INDEX
    Explanations

    Adverbs ending in '-ly' and the word "belied."

    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
    554
    +0.16
    0.7%
    57
    +0.13
    0.6%
    762
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.16
    0.19
    288
    +0.13
    0.21
    99
    +0.12
    0.11
    Negative Logits
    iety
    -0.97
    urnal
    -0.92
    inals
    -0.91
    office
    -0.88
    llan
    -0.87
    INAL
    -0.85
    itives
    -0.82
    xon
    -0.81
    andals
    -0.81
    hibit
    -0.73
    POSITIVE LOGITS
     bel
    0.90
    ayed
    0.83
    iquid
    0.81
    ounge
    0.79
     Carib
    0.79
     pigeon
    0.77
    phe
    0.77
    gian
    0.76
    aying
    0.75
    ittle
    0.73
    Activations Density 5.727%

    No Known Activations