© 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. 29357
    Prev
    Next
    INDEX
    Explanations

    terms related to homeland security and immigration policies

    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
    288
    +0.14
    0.6%
    338
    +0.10
    0.5%
    642
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.03
    146
    +0.10
    0.01
    314
    +0.10
    -0.01
    Negative Logits
     Woodward
    -0.69
     Manit
    -0.67
     Vaj
    -0.65
     Mori
    -0.64
     Bows
    -0.64
     Khe
    -0.64
     deaf
    -0.64
    oths
    -0.64
    bent
    -0.63
     marrow
    -0.63
    POSITIVE LOGITS
     Security
    1.13
    security
    0.99
    istan
    0.96
    Security
    0.95
     security
    0.95
    istani
    0.85
    elligence
    0.80
    ython
    0.75
    eland
    0.75
    ior
    0.72
    Activations Density 0.239%

    No Known Activations