© 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. 30518
    Prev
    Next
    INDEX
    Explanations

    occurrences of the character "Ch" in various contexts

    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
    314
    +0.18
    0.8%
    145
    +0.13
    0.6%
    41
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.18
    0.03
    725
    +0.13
    0.03
    659
    +0.09
    0.02
    Negative Logits
     harness
    -0.74
     Hole
    -0.66
     slic
    -0.65
     peanuts
    -0.65
     anchors
    -0.63
     beware
    -0.63
     Interstellar
    -0.62
     Mechdragon
    -0.62
     nep
    -0.61
    etheless
    -0.61
    POSITIVE LOGITS
    ampions
    1.32
    apters
    1.22
    arity
    1.20
    ampion
    1.16
    ocolate
    1.13
    loe
    1.10
    uckle
    1.10
    rish
    1.09
    ris
    1.08
    ubby
    1.08
    Activations Density 0.097%

    No Known Activations