© 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. 28339
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 'o' 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
    440
    +0.11
    0.5%
    659
    +0.11
    0.5%
    67
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.05
    284
    +0.11
    0.02
    409
    +0.11
    0.02
    Negative Logits
     glim
    -0.83
    t
    -0.73
    lain
    -0.72
     condem
    -0.69
    a
    -0.68
    theless
    -0.67
    s
    -0.65
    r
    -0.63
    channelAvailability
    -0.63
    i
    -0.62
    POSITIVE LOGITS
    zzi
    1.09
    cean
    1.05
    oms
    1.05
    ctor
    1.00
    ebus
    0.96
    emaker
    0.95
    pport
    0.94
    vert
    0.89
    cephal
    0.88
    zzo
    0.86
    Activations Density 0.281%

    No Known Activations