Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 5198
    Prev
    Next
    INDEX
    Explanations

    structural elements in programming languages, particularly in code

    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
    121
    +0.11
    0.5%
    650
    +0.09
    0.4%
    460
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.11
    0.01
    506
    +0.09
    0.01
    691
    +0.08
    0.01
    Negative Logits
    ket
    -0.81
    quit
    -0.77
     Janeiro
    -0.76
    76561
    -0.73
    egg
    -0.72
    Cath
    -0.72
    agonists
    -0.71
    jen
    -0.71
    fal
    -0.70
    rats
    -0.69
    POSITIVE LOGITS
    alth
    0.71
     CoC
    0.69
     Ruin
    0.69
     Diseases
    0.68
     Violent
    0.66
     Representative
    0.66
     Strength
    0.65
     Wealth
    0.65
     Precision
    0.63
     Shape
    0.62
    Activations Density 0.120%

    No Known Activations