© 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. 11263
    Prev
    Next
    INDEX
    Explanations

    content related to the card game "Magic: The Gathering"

    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
    288
    +0.28
    1.0%
    642
    +0.21
    0.8%
    421
    +0.18
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.28
    0.05
    326
    +0.21
    0.04
    642
    +0.18
    0.02
    Negative Logits
    romising
    -0.94
    lishes
    -0.93
    ktop
    -0.84
    gets
    -0.83
     Gork
    -0.82
    OPLE
    -0.82
     Vaugh
    -0.81
     republican
    -0.81
     Fas
    -0.81
     unsub
    -0.78
    POSITIVE LOGITS
     Leap
    1.00
     ILCS
    0.94
    haus
    0.94
    iah
    0.94
    balls
    0.94
    ERY
    0.90
    andise
    0.90
    itic
    0.89
    wagen
    0.89
    ioned
    0.86
    Activations Density 0.456%

    No Known Activations