© 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. 34049
    Prev
    Next
    INDEX
    Explanations

    names of sports teams and athletes

    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
    +0.35
    1.5%
    481
    +0.12
    0.5%
    22
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.35
    0.16
    167
    +0.12
    -0.04
    326
    +0.11
    0.34
    Negative Logits
     Monetary
    -0.67
     eminent
    -0.66
     recess
    -0.64
     Reconstruction
    -0.62
    OPLE
    -0.60
     Confederate
    -0.60
     constitu
    -0.59
     Venezuelan
    -0.58
     Debor
    -0.58
     Sudan
    -0.58
    POSITIVE LOGITS
    iots
    0.78
    nets
    0.73
    onis
    0.71
    hw
    0.69
    nington
    0.69
    amin
    0.68
    uces
    0.68
    rox
    0.67
    croft
    0.67
    ams
    0.66
    Activations Density 21.095%

    No Known Activations