© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29840
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Aaron"

    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
    377
    +0.15
    0.7%
    101
    +0.11
    0.5%
    59
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.15
    0.01
    659
    +0.11
    0.01
    440
    +0.10
    0.01
    Negative Logits
    arget
    -0.81
    rained
    -0.72
    PsyNetMessage
    -0.69
    VALUE
    -0.64
    awaru
    -0.61
    lda
    -0.60
    rag
    -0.60
    geries
    -0.60
    ById
    -0.59
    hospital
    -0.58
    POSITIVE LOGITS
    odox
    0.83
    ica
    0.82
     Burr
    0.81
    女
    0.80
    anth
    0.78
     Finch
    0.77
    thouse
    0.76
    cil
    0.73
     Rodgers
    0.72
    iev
    0.72
    Activations Density 0.123%

    No Known Activations