© 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 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. 28222
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" relating to time and place

    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
    608
    +0.12
    0.6%
    257
    +0.11
    0.5%
    362
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.12
    0.13
    123
    +0.11
    0.13
    257
    +0.10
    0.08
    Negative Logits
    selves
    -0.79
    issance
    -0.77
    ships
    -0.76
     thous
    -0.76
     ACTIONS
    -0.74
    few
    -0.71
    casters
    -0.70
    odox
    -0.69
    wolves
    -0.69
     else
    -0.68
    POSITIVE LOGITS
     hospital
    1.01
     prison
    1.00
     captivity
    0.99
     bed
    0.99
     handcuffs
    0.98
     jail
    0.98
     tears
    0.95
     infancy
    0.95
     1973
    0.93
     Harlem
    0.93
    Activations Density 0.625%

    No Known Activations