© 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. 5313
    Prev
    Next
    INDEX
    Explanations

    the contraction 've' indicating past actions or experiences

    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
    718
    +0.10
    0.5%
    667
    +0.09
    0.4%
    706
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.10
    0.06
    668
    +0.09
    0.05
    183
    +0.09
    0.03
    Negative Logits
     Torrent
    -0.76
    WARD
    -0.66
     replacement
    -0.61
     replacements
    -0.60
     610
    -0.58
    Reviewer
    -0.58
     regards
    -0.58
     DRAGON
    -0.57
    ieu
    -0.57
     Accounts
    -0.56
    POSITIVE LOGITS
     got
    1.23
     gotta
    1.18
    mson
    0.83
    been
    0.82
     gotten
    0.76
    got
    0.72
    igh
    0.72
    eve
    0.70
    ighed
    0.70
    internal
    0.69
    Activations Density 0.139%

    No Known Activations