© 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 EvalsExportsinterp-engineNEWAPI 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. 32513
    Prev
    Next
    INDEX
    Explanations

    demographic information related to age, marital status, and employment

    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
    545
    +0.10
    0.5%
    27
    +0.10
    0.4%
    11
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.10
    0.09
    6
    +0.10
    0.11
    194
    +0.09
    0.07
    Negative Logits
    Operation
    -0.79
     optimization
    -0.76
     sealing
    -0.75
     sabotage
    -0.73
    inventoryQuantity
    -0.72
    ulence
    -0.72
     compressor
    -0.71
    RFC
    -0.71
     takedown
    -0.71
    Reloaded
    -0.71
    POSITIVE LOGITS
    married
    1.28
     Males
    1.23
     Females
    1.23
     ages
    1.20
     aged
    1.16
     spouses
    1.12
    female
    1.12
     Adults
    1.10
     females
    1.10
     married
    1.09
    Activations Density 1.506%

    No Known Activations