© 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. 5017
    Prev
    Next
    INDEX
    Explanations

    occurrences of function definitions in programming context

    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
    152
    +0.10
    0.4%
    558
    +0.10
    0.4%
    433
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.10
    0.01
    356
    +0.10
    0.01
    311
    +0.09
    0.01
    Negative Logits
    stood
    -0.83
    externalActionCode
    -0.76
    cles
    -0.74
    otes
    -0.69
    cled
    -0.68
    ial
    -0.64
    assies
    -0.62
    conn
    -0.62
    rored
    -0.59
     brokers
    -0.59
    POSITIVE LOGITS
    initions
    1.10
    initely
    0.79
    tics
    0.77
    ory
    0.76
    acus
    0.72
    tic
    0.67
    tical
    0.66
    eat
    0.66
    ski
    0.65
    icum
    0.64
    Activations Density 0.049%

    No Known Activations