© 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. 32310
    Prev
    Next
    INDEX
    Explanations

    references to various assistant roles and positions

    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
    624
    +0.12
    0.5%
    136
    +0.12
    0.5%
    167
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    624
    +0.12
    0.02
    752
    +0.12
    0.02
    204
    +0.11
    0.01
    Negative Logits
    abiding
    -0.80
    stakes
    -0.78
    agram
    -0.78
    naires
    -0.76
    naire
    -0.76
    amphetamine
    -0.76
    ibal
    -0.72
    isky
    -0.71
    artifacts
    -0.70
    ktop
    -0.70
    POSITIVE LOGITS
     professor
    1.20
     dean
    0.94
     Professor
    0.92
     secretary
    0.90
     principal
    0.87
     superintendent
    0.86
     professors
    0.85
     director
    0.84
     curator
    0.82
     pastor
    0.78
    Activations Density 0.074%

    No Known Activations