© 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. 28051
    Prev
    Next
    INDEX
    Explanations

    terms related to disabilities and wheelchair usage

    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
    +0.16
    0.7%
    137
    +0.14
    0.6%
    417
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.05
    575
    +0.14
    0.03
    415
    +0.12
    0.02
    Negative Logits
    furt
    -0.83
     Cull
    -0.78
    rils
    -0.76
    76561
    -0.75
     Collider
    -0.75
    unin
    -0.74
    rx
    -0.74
    orically
    -0.73
    ername
    -0.73
    tons
    -0.72
    POSITIVE LOGITS
     rights
    0.80
     impair
    0.78
     Rights
    0.76
     impairment
    0.73
     disabilities
    0.73
     suff
    0.72
     disability
    0.71
     mobility
    0.69
     diagnosis
    0.69
    accessible
    0.67
    Activations Density 0.238%

    No Known Activations