© 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. 29814
    Prev
    Next
    INDEX
    Explanations

    operations related to inserting and manipulating data structures, particularly in programming contexts

    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
    288
    +0.11
    0.5%
    683
    +0.10
    0.5%
    185
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    158
    +0.11
    0.02
    761
    +0.10
    0.02
    526
    +0.10
    -0.00
    Negative Logits
    externalActionCode
    -0.81
    webkit
    -0.74
    iferation
    -0.67
    byss
    -0.65
    ãĥ£
    -0.65
    bey
    -0.65
    llor
    -0.65
    main
    -0.64
    taboola
    -0.64
    runner
    -0.64
    POSITIVE LOGITS
    ional
    0.85
     INTO
    0.84
    itional
    0.82
    ion
    0.81
    icut
    0.78
    ions
    0.76
     into
    0.74
    utions
    0.73
    into
    0.72
    urized
    0.72
    Activations Density 0.154%

    No Known Activations