© 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. 4798
    Prev
    Next
    INDEX
    Explanations

    terms related to excitement or trends

    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
    288
    +0.11
    0.5%
    314
    +0.11
    0.5%
    422
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.05
    271
    +0.11
    0.03
    544
    +0.10
    0.02
    Negative Logits
    ania
    -0.68
    istries
    -0.64
    icts
    -0.62
    ocese
    -0.60
     extrem
    -0.60
     imperfect
    -0.59
     TAMADRA
    -0.59
    nesota
    -0.59
    arium
    -0.58
    arians
    -0.58
    POSITIVE LOGITS
    bub
    0.83
    phal
    0.78
    leading
    0.78
    phrase
    0.77
    word
    0.74
     frenzy
    0.74
     surrounding
    0.74
    aic
    0.73
     anticipation
    0.73
    worthy
    0.73
    Activations Density 0.241%

    No Known Activations