© 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. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 7726
    Prev
    Next
    INDEX
    Explanations

    references to popular video games and their franchises

    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
    359
    +0.11
    0.5%
    662
    +0.10
    0.5%
    297
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    556
    +0.11
    0.04
    288
    +0.10
    0.04
    359
    +0.10
    0.03
    Negative Logits
    shr
    -0.91
    rist
    -0.85
    erv
    -0.82
    kj
    -0.79
    abo
    -0.76
    aber
    -0.74
    resh
    -0.69
    lace
    -0.69
    opt
    -0.69
    tem
    -0.68
    POSITIVE LOGITS
     III
    0.92
     Primal
    0.87
    ®
    0.84
     IV
    0.83
     358
    0.79
     4
    0.78
     ®
    0.73
     Generations
    0.72
     Jr
    0.71
     3
    0.70
    Activations Density 0.231%

    No Known Activations