© 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 EvalsExportsAPI 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. 6388
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting commonly used in code or markup languages

    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
    264
    +0.10
    0.5%
    478
    +0.10
    0.4%
    22
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.10
    0.04
    160
    +0.10
    0.04
    701
    +0.10
    0.02
    Negative Logits
    etheless
    -0.82
     hatched
    -0.76
    sembly
    -0.74
     coerced
    -0.73
     cooled
    -0.71
    inarily
    -0.71
     polarized
    -0.70
     hither
    -0.69
     depended
    -0.69
     indirectly
    -0.69
    POSITIVE LOGITS
    USER
    0.87
    Example
    0.73
     Example
    0.71
     Profile
    0.70
     Variety
    0.70
    Admin
    0.70
    Project
    0.70
    example
    0.69
    john
    0.67
    Synopsis
    0.67
    Activations Density 0.184%

    No Known Activations