© 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. 11315
    Prev
    Next
    INDEX
    Explanations

    phrases related to card effects and game mechanics, particularly in a card-based game context

    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
    +0.21
    0.7%
    640
    +0.16
    0.5%
    102
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    578
    +0.21
    0.02
    103
    +0.16
    0.03
    637
    +0.16
    0.03
    Negative Logits
     Sakuya
    -1.13
    wagen
    -1.10
     Sidd
    -1.10
     Jenner
    -1.05
     Pearce
    -1.03
     Nikon
    -1.02
     Canaver
    -1.00
     Khe
    -0.99
     Gillespie
    -0.99
     Lazarus
    -0.98
    POSITIVE LOGITS
    Ħ¢
    2.13
    ĵ
    1.74
    ¥ŀ
    1.73
    ł
    1.71
    ĵĺ
    1.67
    ŀ
    1.67
    Ĥª
    1.60
    §
    1.58
    Ķ
    1.56
    Ĵ
    1.54
    Activations Density 0.482%

    No Known Activations