© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29530
    Prev
    Next
    INDEX
    Explanations

    references to geographic regions

    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
    651
    +0.10
    0.4%
    219
    +0.10
    0.4%
    318
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.03
    495
    +0.10
    0.02
    459
    +0.09
    0.02
    Negative Logits
    lihood
    -0.80
    glers
    -0.73
    ument
    -0.68
    vous
    -0.67
    gers
    -0.65
    tails
    -0.65
     Dame
    -0.65
    ãĥīãĥ©
    -0.64
    tons
    -0.62
    posed
    -0.62
    POSITIVE LOGITS
    ally
    1.29
    als
    1.17
    wide
    0.96
    ality
    0.89
    ESE
    0.86
    alf
    0.80
    ale
    0.78
    ALS
    0.75
    naire
    0.75
    ional
    0.75
    Activations Density 0.122%

    No Known Activations