© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5293
    Prev
    Next
    INDEX
    Explanations

    references to task forces and commissions

    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
    31
    +0.11
    0.5%
    397
    +0.11
    0.5%
    691
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    31
    +0.11
    0.05
    247
    +0.11
    0.05
    644
    +0.10
    0.05
    Negative Logits
     axle
    -0.67
     Advantage
    -0.65
     dehyd
    -0.65
     DRM
    -0.64
     foil
    -0.64
     baff
    -0.64
     reuse
    -0.62
     gel
    -0.62
     Incarnation
    -0.61
     upd
    -0.60
    POSITIVE LOGITS
     convened
    1.28
     chaired
    1.25
     investigating
    1.03
     tasked
    0.97
     disbanded
    0.95
     deliberations
    0.93
     headed
    0.93
    chairs
    0.90
     appointed
    0.88
     probing
    0.88
    Activations Density 0.317%

    No Known Activations