© 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. 36326
    Prev
    Next
    INDEX
    Explanations

    specific body parts, particularly focusing on the neck

    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
    +0.17
    0.8%
    587
    +0.11
    0.5%
    285
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.17
    0.11
    314
    +0.11
    -0.05
    141
    +0.11
    0.06
    Negative Logits
    ========
    -0.65
    ordinary
    -0.64
    urity
    -0.64
    ptions
    -0.63
    venants
    -0.60
     Parenthood
    -0.59
    astical
    -0.59
    ISE
    -0.59
     Mile
    -0.59
    Magikarp
    -0.58
    POSITIVE LOGITS
    lace
    1.31
    tie
    1.24
    beard
    1.16
    lines
    1.10
    bones
    1.05
    line
    1.05
    bone
    1.00
    guards
    0.87
    guard
    0.84
    lining
    0.81
    Activations Density 7.324%

    No Known Activations