© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 4988
    Prev
    Next
    INDEX
    Explanations

    terms related to abilities, skills, and powers in a gaming or fantasy context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    575
    +0.12
    0.5%
    214
    +0.12
    0.5%
    194
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.05
    255
    +0.12
    0.04
    575
    +0.10
    0.04
    Negative Logits
     closures
    -0.76
    izen
    -0.75
    lees
    -0.74
     sched
    -0.71
     Cater
    -0.67
    axies
    -0.66
     assemb
    -0.66
     embry
    -0.65
     redund
    -0.64
     benz
    -0.61
    POSITIVE LOGITS
    erity
    0.90
     Rating
    0.89
    Factor
    0.87
    Bonus
    0.87
     Improvement
    0.82
    Rating
    0.78
     quot
    0.78
    Rate
    0.77
     modifier
    0.76
    Boost
    0.73
    Activations Density 0.212%

    No Known Activations