© 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. 5004
    Prev
    Next
    INDEX
    Explanations

    terms related to null values or undefined behavior in programming contexts

    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
    178
    +0.11
    0.5%
    688
    +0.11
    0.5%
    740
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    178
    +0.11
    0.01
    137
    +0.11
    0.01
    713
    +0.11
    0.01
    Negative Logits
     Remastered
    -0.75
    akov
    -0.72
     hemor
    -0.71
    ilitating
    -0.69
    DonaldTrump
    -0.68
    BOOK
    -0.68
     toget
    -0.68
     exha
    -0.67
    xual
    -0.67
     Flavoring
    -0.64
    POSITIVE LOGITS
    ptr
    1.33
    ifying
    1.19
    ified
    1.17
    ification
    1.10
    ifies
    1.09
    ifier
    1.05
    ifiers
    1.02
    ify
    1.00
    ity
    0.94
    ality
    0.92
    Activations Density 0.041%

    No Known Activations