© 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. 8141
    Prev
    Next
    INDEX
    Explanations

    the verb "go" and its variations, indicating movement or transition

    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
    377
    +0.13
    0.6%
    354
    +0.11
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    377
    +0.13
    0.10
    354
    +0.11
    0.10
    200
    +0.10
    0.09
    Negative Logits
    ullah
    -0.74
    eers
    -0.70
    ament
    -0.68
     Horus
    -0.63
    creen
    -0.63
    eer
    -0.60
    lain
    -0.59
    Lat
    -0.58
    ificent
    -0.56
    hold
    -0.56
    POSITIVE LOGITS
    verning
    1.10
    vt
    1.04
    ggle
    1.02
    lems
    0.99
     overboard
    0.97
     unnoticed
    0.90
     forth
    0.89
     ahead
    0.88
     forward
    0.87
     ashore
    0.84
    Activations Density 0.202%

    No Known Activations