© 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. 7670
    Prev
    Next
    INDEX
    Explanations

    brackets or parentheses in the text

    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
    640
    +0.11
    0.5%
    551
    +0.10
    0.5%
    373
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    627
    +0.11
    0.05
    160
    +0.10
    0.07
    640
    +0.10
    0.06
    Negative Logits
     viz
    -0.78
     largeDownload
    -0.74
    ioned
    -0.73
    meaning
    -0.72
    >.
    -0.70
    CLASSIFIED
    -0.68
    \<
    -0.68
     equival
    -0.67
    making
    -0.66
     ].
    -0.65
    POSITIVE LOGITS
    isoft
    0.97
    gamer
    0.96
    Nitrome
    0.87
    Nintendo
    0.78
    Mobile
    0.77
    inct
    0.76
    Software
    0.75
    ORPG
    0.73
    gae
    0.70
    Arcade
    0.70
    Activations Density 0.225%

    No Known Activations