© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 7134
    Prev
    Next
    INDEX
    Explanations

    words related to the team "Stars"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    578
    +0.10
    0.7%
    386
    +0.08
    0.5%
    553
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.09
    288
    +0.08
    0.09
    678
    +0.07
    0.05
    Negative Logits
    ufact
    -0.68
    vice
    -0.49
    ctors
    -0.46
    yrus
    -0.45
    rection
    -0.44
    isin
    -0.44
    ibaba
    -0.44
    uthor
    -0.44
    arthed
    -0.43
    agin
    -0.42
    POSITIVE LOGITS
    cream
    0.87
    hips
    0.81
    night
    0.66
    manship
    0.61
    ilver
    0.60
    ystem
    0.59
    ource
    0.57
    mith
    0.56
    peak
    0.54
     Stars
    0.54
    Activations Density 1.092%

    No Known Activations