© 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. 5436
    Prev
    Next
    INDEX
    Explanations

    numerical data and references within the text

    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
    373
    +0.14
    0.6%
    365
    +0.09
    0.4%
    372
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.14
    -0.02
    472
    +0.09
    0.01
    717
    +0.09
    0.01
    Negative Logits
    chenko
    -0.74
     Died
    -0.61
    SHARE
    -0.59
     Nanto
    -0.59
    ankind
    -0.59
    ukemia
    -0.59
    razil
    -0.59
    ãĤ®
    -0.58
    wolves
    -0.57
    holes
    -0.57
    POSITIVE LOGITS
     cooldown
    0.66
    RIPT
    0.65
    969
    0.65
    irmation
    0.63
     DevOnline
    0.61
    à©
    0.60
    ãģ®æ
    0.60
     Mub
    0.59
    eteenth
    0.59
     script
    0.57
    Activations Density 0.084%

    No Known Activations