© 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. 29379
    Prev
    Next
    INDEX
    Explanations

    references to individuals, particularly those named Herz

    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
    261
    +0.12
    0.5%
    289
    +0.10
    0.5%
    598
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.01
    288
    +0.10
    0.01
    232
    +0.10
    0.01
    Negative Logits
    tti
    -0.72
    ibles
    -0.71
    ibility
    -0.70
    kson
    -0.69
    rill
    -0.68
    rha
    -0.65
    ingo
    -0.63
    mber
    -0.63
    vable
    -0.63
    teen
    -0.62
    POSITIVE LOGITS
    osp
    0.79
    ervative
    0.78
    els
    0.71
    omen
    0.70
    ets
    0.70
    Org
    0.69
    obyl
    0.69
    izer
    0.68
    olith
    0.67
    isting
    0.67
    Activations Density 0.034%

    No Known Activations