© 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. 28380
    Prev
    Next
    INDEX
    Explanations

    pronouns indicating possession and references to individuals

    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
    362
    +0.11
    0.5%
    330
    +0.11
    0.5%
    92
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.11
    0.11
    15
    +0.11
    0.09
    608
    +0.10
    0.10
    Negative Logits
    umblr
    -0.79
    emort
    -0.74
    orial
    -0.70
    ibaba
    -0.69
    uzzle
    -0.69
    @#
    -0.68
    Contents
    -0.64
    urations
    -0.64
     CrossRef
    -0.63
    WOR
    -0.63
    POSITIVE LOGITS
     client
    1.18
     colleague
    1.14
     nephew
    1.05
     daughter
    1.02
     son
    1.01
     clients
    0.98
     husband
    0.96
     grandson
    0.94
     niece
    0.93
     granddaughter
    0.90
    Activations Density 0.760%

    No Known Activations