© 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. 27033
    Prev
    Next
    INDEX
    Explanations

    nouns related to electronic components and their specifications

    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
    459
    +0.12
    0.5%
    589
    +0.10
    0.5%
    27
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.26
    459
    +0.10
    0.08
    326
    +0.10
    0.23
    Negative Logits
    RESULTS
    -0.93
     subsequent
    -0.80
    onement
    -0.77
     resumed
    -0.75
     deepening
    -0.75
     continued
    -0.72
     elapsed
    -0.72
     ensuing
    -0.70
     vanquished
    -0.68
     timely
    -0.68
    POSITIVE LOGITS
     kinda
    1.20
     ;)
    1.10
     doesnt
    1.07
     stuff
    1.06
     crap
    1.04
     thats
    1.03
     haha
    0.98
     :)
    0.95
     guy
    0.92
     dunno
    0.91
    Activations Density 7.693%

    No Known Activations