© 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. 10-RES_POST_32K-OAI
    11. 28913
    Prev
    Next
    INDEX
    Explanations

    punctuation and structural elements in the text

    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
    373
    +0.17
    0.8%
    189
    +0.10
    0.4%
    89
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.17
    0.14
    640
    +0.10
    0.14
    496
    +0.10
    0.13
    Negative Logits
     Cosponsors
    -0.87
    rawdownloadcloneembedreportprint
    -0.78
    quished
    -0.77
    Orig
    -0.68
     ?)
    -0.68
    ktop
    -0.67
    STAR
    -0.65
    Poké
    -0.64
    NEY
    -0.63
    ARDIS
    -0.62
    POSITIVE LOGITS
     secondly
    1.61
     Secondly
    1.56
    Secondly
    1.37
     Second
    1.19
     second
    1.02
    Second
    0.94
    second
    0.81
     ii
    0.72
     Alternatively
    0.65
    middle
    0.63
    Activations Density 2.906%

    No Known Activations