© 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. 7587
    Prev
    Next
    INDEX
    Explanations

    instances of formal speaking engagements or addresses

    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
    690
    +0.12
    0.5%
    310
    +0.10
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.12
    0.06
    242
    +0.10
    0.04
    760
    +0.10
    0.03
    Negative Logits
    ective
    -0.65
    leys
    -0.65
     mess
    -0.65
     ILCS
    -0.64
     glances
    -0.63
     scans
    -0.63
     esc
    -0.62
     tatt
    -0.62
     smugg
    -0.62
     Healer
    -0.61
    POSITIVE LOGITS
     commencement
    0.96
     keynote
    0.96
     inaugural
    0.82
     speeches
    0.78
     podium
    0.78
     televised
    0.78
     Lect
    0.76
     graduating
    0.76
     denouncing
    0.76
     attendees
    0.75
    Activations Density 1.151%

    No Known Activations