© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31575
    Prev
    Next
    INDEX
    Explanations

    references related to geographical locations or positions

    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
    414
    +0.11
    0.5%
    373
    +0.11
    0.5%
    459
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.11
    0.06
    108
    +0.11
    0.05
    287
    +0.10
    0.05
    Negative Logits
     Cosponsors
    -0.86
    enaries
    -0.79
    zes
    -0.66
     bonuses
    -0.66
    iets
    -0.65
    soDeliveryDate
    -0.64
     sauces
    -0.64
    artifacts
    -0.63
     Donation
    -0.61
    Enabled
    -0.61
    POSITIVE LOGITS
     earth
    1.59
     planet
    1.44
     Earth
    1.40
    Earth
    1.20
     Planet
    0.99
    earth
    0.98
     record
    0.91
    planet
    0.88
     EAR
    0.88
    record
    0.80
    Activations Density 0.444%

    No Known Activations