© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29684
    Prev
    Next
    INDEX
    Explanations

    references to documents, articles, and reports that contain sensitive or significant information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    756
    +0.14
    0.6%
    40
    +0.09
    0.4%
    556
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.14
    0.15
    498
    +0.09
    0.09
    756
    +0.09
    -0.01
    Negative Logits
    issance
    -0.89
    ourney
    -0.76
    morrow
    -0.73
     Flavoring
    -0.72
    iem
    -0.72
    EStream
    -0.71
    ecast
    -0.71
    luck
    -0.70
    duino
    -0.67
    uel
    -0.67
    POSITIVE LOGITS
     references
    1.53
     mention
    1.44
     wording
    1.28
     clauses
    1.26
     paragraphs
    1.26
     passages
    1.26
     mentions
    1.22
     footnote
    1.19
    emphasis
    1.18
     citations
    1.17
    Activations Density 3.380%

    No Known Activations