© 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 EvalsExportsAPI 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. 6779
    Prev
    Next
    INDEX
    Explanations

    references to specific names or identifiers, particularly those starting with "Sam" or "Tim"

    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
    26
    +0.12
    0.6%
    370
    +0.12
    0.6%
    439
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.03
    167
    +0.12
    0.01
    683
    +0.10
    0.02
    Negative Logits
     brace
    -0.78
     Force
    -0.68
     Advent
    -0.66
     monkey
    -0.66
     div
    -0.65
     shroud
    -0.64
     flared
    -0.64
     LEDs
    -0.64
     LED
    -0.63
     Emir
    -0.62
    POSITIVE LOGITS
    elong
    1.07
    eto
    1.05
    ania
    0.99
    eta
    0.99
    etime
    0.97
    elin
    0.97
    est
    0.95
    ither
    0.95
    esis
    0.93
    anz
    0.92
    Activations Density 0.044%

    No Known Activations