© 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. 11784
    Prev
    Next
    INDEX
    Explanations

    triggers related to playing a collectible card game, with mentions of cards entering the battlefield and dealing damage

    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
    483
    +0.04
    0.5%
    749
    +0.03
    0.4%
    28
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    530
    +0.04
    0.01
    362
    +0.03
    0.01
    526
    +0.03
    0.00
    Negative Logits
     Liang
    -0.26
    escent
    -0.25
    wana
    -0.24
    kered
    -0.23
    edition
    -0.23
    jiang
    -0.23
    etter
    -0.23
    etimes
    -0.22
    redd
    -0.22
    ovie
    -0.22
    POSITIVE LOGITS
    sburgh
    0.27
    ashington
    0.23
    Ward
    0.23
     Gast
    0.23
    ipes
    0.23
     Plaza
    0.23
    ropy
    0.22
    ï
    0.22
    ventory
    0.21
    Exit
    0.21
    Activations Density 0.055%

    No Known Activations