© 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. 5145
    Prev
    Next
    INDEX
    Explanations

    actions related to movement or travel

    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
    454
    +0.13
    0.6%
    363
    +0.13
    0.6%
    373
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    377
    +0.13
    0.07
    437
    +0.13
    0.05
    354
    +0.12
    0.05
    Negative Logits
     proceeding
    -0.68
     trending
    -0.67
     Decay
    -0.65
    pers
    -0.65
     attrition
    -0.65
     fluid
    -0.64
    sels
    -0.63
     dissip
    -0.63
     toast
    -0.63
    redo
    -0.62
    POSITIVE LOGITS
     visit
    0.95
    packing
    0.82
     visited
    0.80
     visiting
    0.78
     visits
    0.78
    ivan
    0.75
     Tours
    0.74
     scout
    0.71
     shopping
    0.70
     inspect
    0.70
    Activations Density 0.191%

    No Known Activations