© 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. 31061
    Prev
    Next
    INDEX
    Explanations

    instances of people eavesdropping or overhearing conversations

    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
    206
    +0.09
    0.4%
    564
    +0.09
    0.4%
    513
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.09
    -0.00
    555
    +0.09
    0.02
    365
    +0.09
    0.01
    Negative Logits
    UES
    -0.86
    ues
    -0.84
    uously
    -0.83
    UE
    -0.82
    esse
    -0.79
    uese
    -0.78
    ãĥĩ
    -0.76
    kie
    -0.76
    gery
    -0.73
    ger
    -0.73
    POSITIVE LOGITS
    arse
    0.93
    aring
    0.91
    onding
    0.81
    arer
    0.77
     overhe
    0.74
    °
    0.73
    charging
    0.73
    ating
    0.73
    arms
    0.71
    rought
    0.69
    Activations Density 0.208%

    No Known Activations