© 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. 6526
    Prev
    Next
    INDEX
    Explanations

    statements asserting the truth or validity of various claims or observations

    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
    700
    +0.11
    0.5%
    302
    +0.10
    0.5%
    82
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.11
    0.03
    718
    +0.10
    0.04
    274
    +0.10
    0.03
    Negative Logits
     ILCS
    -0.72
     inception
    -0.59
     initiation
    -0.58
    ded
    -0.57
    vironment
    -0.57
     curfew
    -0.56
     acquisitions
    -0.55
     diarr
    -0.55
     pursuant
    -0.55
    ciating
    -0.53
    POSITIVE LOGITS
     applies
    0.75
     apply
    0.69
    VB
    0.66
    ÄŁ
    0.65
    Ĥ¬
    0.65
    senal
    0.63
     prev
    0.62
    Ð
    0.62
    umann
    0.62
    ñ
    0.61
    Activations Density 0.431%

    No Known Activations