© 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. 5266
    Prev
    Next
    INDEX
    Explanations

    mentions of coworkers or peers within an organization

    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
    420
    +0.12
    0.5%
    488
    +0.12
    0.5%
    285
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.12
    0.03
    679
    +0.12
    0.02
    146
    +0.11
    0.02
    Negative Logits
    skinned
    -0.73
     Tycoon
    -0.66
    istor
    -0.64
     Pwr
    -0.63
    acco
    -0.62
    Interstitial
    -0.61
    issan
    -0.61
    apor
    -0.60
     emanc
    -0.60
    tarians
    -0.60
    POSITIVE LOGITS
     colleagues
    0.89
     colleague
    0.89
    ries
    0.86
     coworkers
    0.75
    rity
    0.75
    onym
    0.71
    ratulations
    0.70
    pai
    0.70
    ority
    0.66
    heses
    0.66
    Activations Density 0.077%

    No Known Activations