© 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. 33872
    Prev
    Next
    INDEX
    Explanations

    words related to indulgence or indulging in various contexts, such as spiritual indulgence, political indulgence, and personal indulgence

    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
    151
    +0.14
    0.7%
    348
    +0.10
    0.5%
    0
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.14
    0.21
    442
    +0.10
    0.10
    288
    +0.09
    0.23
    Negative Logits
    eworks
    -0.66
    iped
    -0.64
    nea
    -0.64
    owe
    -0.59
    apixel
    -0.59
    iop
    -0.59
    eting
    -0.59
    adena
    -0.58
    ework
    -0.58
    icians
    -0.57
    POSITIVE LOGITS
    gence
    1.05
    gent
    0.73
    gently
    0.73
    gencies
    0.69
    ga
    0.66
    INE
    0.65
    zeb
    0.64
    GER
    0.64
    HI
    0.61
     Clicker
    0.61
    Activations Density 9.306%

    No Known Activations