© 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. 7739
    Prev
    Next
    INDEX
    Explanations

    descriptions of shape and size characteristics

    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
    +0.11
    0.5%
    544
    +0.11
    0.5%
    42
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.11
    0.09
    393
    +0.11
    0.09
    83
    +0.10
    0.05
    Negative Logits
    gencies
    -0.97
    arcity
    -0.76
    autions
    -0.74
    antics
    -0.73
    idates
    -0.72
    genre
    -0.72
    priority
    -0.71
     sourcing
    -0.71
    Avg
    -0.70
    Marginal
    -0.70
    POSITIVE LOGITS
     humanoid
    1.15
     skull
    0.95
     tentacles
    0.94
     flesh
    0.94
     claws
    0.94
     resembling
    0.92
    osaurus
    0.90
     wings
    0.88
     skulls
    0.87
     spherical
    0.86
    Activations Density 1.215%

    No Known Activations