Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 5101
    Prev
    Next
    INDEX
    Explanations

    terms 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
    566
    +0.18
    0.7%
    216
    +0.12
    0.5%
    635
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.10
    326
    +0.12
    0.08
    343
    +0.12
    0.06
    Negative Logits
    lihood
    -1.08
    igating
    -1.02
    sworth
    -1.01
    EngineDebug
    -0.94
    igation
    -0.92
    edly
    -0.91
    gling
    -0.89
    hood
    -0.84
    wise
    -0.83
    mark
    -0.81
    POSITIVE LOGITS
    ffee
    0.90
    ategory
    0.90
    avorite
    0.89
    olla
    0.88
    ateg
    0.86
    etz
    0.85
    unta
    0.84
    onte
    0.83
    zzi
    0.80
     Malfoy
    0.80
    Activations Density 1.044%

    No Known Activations