© 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
    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. 40688
    Prev
    Next
    INDEX
    Explanations

    names of people, places, and events, likely from a dataset with diverse information

    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
    +0.29
    1.3%
    365
    +0.11
    0.5%
    696
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.29
    0.28
    580
    +0.11
    0.11
    288
    +0.10
    0.24
    Negative Logits
    士
    -0.77
    ingham
    -0.75
    EVA
    -0.71
     Gamble
    -0.69
    SHIP
    -0.68
    è¦ļéĨĴ
    -0.67
     Healer
    -0.65
     Accountability
    -0.64
     Elves
    -0.63
    nature
    -0.63
    POSITIVE LOGITS
    umen
    0.92
    cean
    0.90
    anium
    0.85
    mble
    0.81
    umin
    0.81
    oj
    0.81
    isoft
    0.80
    yssey
    0.79
    uth
    0.79
    enium
    0.79
    Activations Density 15.091%

    No Known Activations