© 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. 14020
    Prev
    Next
    INDEX
    Explanations

    specific names and terms related to entertainment, community, and medical conditions

    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
    343
    +0.12
    0.6%
    102
    +0.10
    0.5%
    738
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.22
    326
    +0.10
    0.20
    343
    +0.10
    0.11
    Negative Logits
    ::::::::
    -0.65
     Dice
    -0.62
    ::::
    -0.57
    thia
    -0.55
    ãĤ´ãĥ³
    -0.54
     Bike
    -0.54
     Isles
    -0.53
    onsense
    -0.53
     Tire
    -0.52
    ãĥĩãĤ£
    -0.52
    POSITIVE LOGITS
    riel
    0.98
    imental
    0.87
    rams
    0.75
    rants
    0.74
    les
    0.73
    rets
    0.72
    iosity
    0.72
    iants
    0.72
    inia
    0.71
    ran
    0.71
    Activations Density 6.585%

    No Known Activations