© 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. 35624
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and actions in code

    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
    461
    +0.04
    0.4%
    496
    +0.04
    0.4%
    188
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    615
    +0.04
    0.09
    640
    +0.04
    0.19
    373
    +0.04
    -0.17
    Negative Logits
    seys
    -0.40
    ;;;;;;;;;;;;
    -0.33
    ilage
    -0.33
     rook
    -0.32
    AG
    -0.31
    tein
    -0.30
     row
    -0.30
     SOLD
    -0.29
    onet
    -0.29
    onym
    -0.29
    POSITIVE LOGITS
    Minecraft
    0.45
    FML
    0.42
    Ore
    0.39
    Chicken
    0.35
    Textures
    0.34
     Ender
    0.34
    SourceFile
    0.34
     EntityItem
    0.33
    addons
    0.33
    ForgeModLoader
    0.33
    Activations Density 7.751%

    No Known Activations