© 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. 8095
    Prev
    Next
    INDEX
    Explanations

    specific symbols and keywords often used in formatting or highlighting 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
    227
    +0.11
    0.5%
    376
    +0.11
    0.5%
    387
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.11
    0.02
    316
    +0.11
    0.02
    742
    +0.10
    0.02
    Negative Logits
    ttes
    -0.80
     Flavoring
    -0.79
    oons
    -0.73
    anmar
    -0.72
    cart
    -0.71
    theless
    -0.70
     externalToEVAOnly
    -0.67
    é¾įå
    -0.65
    rev
    -0.64
    lights
    -0.62
    POSITIVE LOGITS
    inventoryQuantity
    0.70
    Listen
    0.69
    Too
    0.68
    Fat
    0.66
    Don
    0.64
    Thank
    0.64
    Empty
    0.64
    hovah
    0.64
    Damn
    0.63
    Alright
    0.63
    Activations Density 0.086%

    No Known Activations