© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5229
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Rush" and associated references, particularly to Rush Limbaugh

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    385
    +0.13
    0.6%
    710
    +0.12
    0.5%
    218
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.02
    444
    +0.12
    0.01
    374
    +0.10
    0.01
    Negative Logits
     FANT
    -0.74
     MFT
    -0.66
     bom
    -0.63
     sealed
    -0.63
     Klaus
    -0.59
     packaged
    -0.59
     flashing
    -0.58
     Consent
    -0.58
     bount
    -0.57
     conflicted
    -0.56
    POSITIVE LOGITS
     Limbaugh
    1.26
    die
    1.15
    cliffe
    1.05
     Hour
    0.93
    more
    0.90
    anism
    0.89
    itant
    0.89
    lett
    0.88
    brush
    0.83
    itude
    0.83
    Activations Density 0.092%

    No Known Activations