© 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. 5248
    Prev
    Next
    INDEX
    Explanations

    quantitative estimates and numerical data related to populations or statistics

    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
    518
    +0.11
    0.5%
    431
    +0.11
    0.5%
    496
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    405
    +0.11
    0.06
    333
    +0.11
    0.05
    165
    +0.10
    0.03
    Negative Logits
     Kelvin
    -0.70
    IVER
    -0.70
    estamp
    -0.67
    ratulations
    -0.67
     Pastebin
    -0.66
    ierre
    -0.62
    ait
    -0.60
    ots
    -0.60
    eon
    -0.58
    ãĤĵ
    -0.58
    POSITIVE LOGITS
     fatalities
    0.73
     underestimate
    0.70
     unexpl
    0.67
     Strait
    0.66
     Schne
    0.66
     wart
    0.65
    gross
    0.61
     morbid
    0.61
     aver
    0.60
     human
    0.58
    Activations Density 1.091%

    No Known Activations