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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7497
    Prev
    Next
    INDEX
    Explanations

    punctuations and end of sentences, particularly in dialogues

    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
    314
    +0.17
    0.8%
    373
    +0.17
    0.8%
    419
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    426
    +0.17
    0.10
    352
    +0.17
    0.10
    280
    +0.10
    0.10
    Negative Logits
     disadvant
    -0.65
     congr
    -0.61
     populated
    -0.60
     uniqueness
    -0.59
     autobi
    -0.59
     pse
    -0.58
    naissance
    -0.57
    ATURES
    -0.56
     adolesc
    -0.56
     perspect
    -0.55
    POSITIVE LOGITS
    ↵
    0.76
     âĢķ
    0.73
    ãĢı
    0.64
    ï¸
    0.61
    answered
    0.59
    resh
    0.59
    Unix
    0.58
    Sharp
    0.58
    .}
    0.57
    ache
    0.57
    Activations Density 0.354%

    No Known Activations