© 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. 27692
    Prev
    Next
    INDEX
    Explanations

    phrases involving the verb "have" and its various forms

    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
    246
    +0.09
    0.4%
    245
    +0.09
    0.4%
    235
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.09
    0.11
    344
    +0.09
    0.11
    668
    +0.09
    0.10
    Negative Logits
    united
    -0.74
     surv
    -0.70
     Izan
    -0.69
    achu
    -0.65
     seiz
    -0.65
     SERV
    -0.64
    amera
    -0.64
     inval
    -0.64
    berus
    -0.64
    Released
    -0.63
    POSITIVE LOGITS
     doubts
    1.11
     misconceptions
    1.01
     suspicions
    0.97
     concerns
    0.95
     misconception
    0.95
     precon
    0.94
     skepticism
    0.94
     trouble
    0.93
     concern
    0.92
     aversion
    0.91
    Activations Density 0.554%

    No Known Activations