© 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. 40659
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names of individuals or characters

    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
    99
    +0.14
    0.6%
    571
    +0.13
    0.5%
    607
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.17
    99
    +0.13
    0.09
    326
    +0.12
    0.17
    Negative Logits
    ¥µ
    -0.77
     caul
    -0.71
    eca
    -0.71
    ascus
    -0.69
     congestion
    -0.69
     cabbage
    -0.68
     cultivate
    -0.68
     Aven
    -0.67
     Licensed
    -0.66
    isco
    -0.66
    POSITIVE LOGITS
    otle
    1.26
    yll
    1.19
    iasis
    1.17
    uania
    1.10
    urst
    1.08
    iop
    1.03
    gow
    1.02
    ril
    1.02
    ttp
    1.02
    itudinal
    1.01
    Activations Density 5.444%

    No Known Activations