© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5251
    Prev
    Next
    INDEX
    Explanations

    quantitative measures and numerical data

    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
    501
    +0.13
    0.6%
    407
    +0.11
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.13
    0.09
    37
    +0.11
    0.07
    675
    +0.10
    0.07
    Negative Logits
    aceae
    -0.89
    omorphic
    -0.86
    udo
    -0.80
    '/
    -0.76
    cients
    -0.75
    omorph
    -0.73
    onite
    -0.72
    mallow
    -0.71
    Ħ¢
    -0.70
    cial
    -0.69
    POSITIVE LOGITS
    Express
    0.73
    BuyableInstoreAndOnline
    0.66
    ahime
    0.66
     redeem
    0.63
    Transaction
    0.61
     expenses
    0.60
     freeing
    0.59
     Allow
    0.58
    Default
    0.57
     Transactions
    0.57
    Activations Density 0.302%

    No Known Activations