© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 29862
    Prev
    Next
    INDEX
    Explanations

    references to the term "immediate."

    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
    105
    +0.11
    0.5%
    728
    +0.11
    0.5%
    96
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.11
    0.01
    616
    +0.11
    0.01
    256
    +0.10
    0.01
    Negative Logits
    cius
    -0.84
    ramids
    -0.73
    doctor
    -0.71
    MET
    -0.70
    unal
    -0.68
    _-
    -0.68
    itely
    -0.67
    rar
    -0.67
     Scher
    -0.65
    smanship
    -0.64
    POSITIVE LOGITS
     gratification
    1.19
    aneously
    1.07
     aftermath
    0.98
     vicinity
    0.96
     surroundings
    0.85
     reaction
    0.84
     threat
    0.80
     danger
    0.79
    aneous
    0.78
     succession
    0.76
    Activations Density 0.049%

    No Known Activations