© 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. 8-RES_POST_32K-OAI
    11. 8242
    Prev
    Next
    INDEX
    Explanations

    mentions related to government funding and appropriations

    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
    373
    +0.15
    0.7%
    306
    +0.11
    0.5%
    292
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    680
    +0.15
    0.01
    306
    +0.11
    0.02
    31
    +0.10
    0.02
    Negative Logits
    alore
    -0.73
    £ı
    -0.66
    afer
    -0.64
    rial
    -0.63
    eport
    -0.62
    osate
    -0.61
     fault
    -0.61
    estate
    -0.60
    cellence
    -0.60
    CTV
    -0.58
    POSITIVE LOGITS
     Cosponsors
    0.85
     <<
    0.84
     Dollars
    0.77
     appropriated
    0.68
    mire
    0.64
     Projects
    0.64
     Committees
    0.64
    ikes
    0.62
    arag
    0.62
     committees
    0.62
    Activations Density 0.150%

    No Known Activations