© 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. 31737
    Prev
    Next
    INDEX
    Explanations

    numeric data related to indices or statistical measures

    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
    373
    +0.18
    0.9%
    412
    +0.13
    0.6%
    761
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.18
    0.04
    314
    +0.13
    -0.01
    317
    +0.10
    0.03
    Negative Logits
    anche
    -0.63
     segregation
    -0.60
     acupuncture
    -0.59
     rooting
    -0.59
    ances
    -0.59
    inventoryQuantity
    -0.59
    etheless
    -0.59
     assassination
    -0.57
     ObamaCare
    -0.56
     ALEC
    -0.56
    POSITIVE LOGITS
    wat
    0.81
    pta
    0.76
    ttes
    0.76
    Äĩ
    0.72
    pt
    0.71
    tti
    0.71
    jad
    0.70
    smith
    0.70
    wk
    0.70
     pc
    0.70
    Activations Density 0.304%

    No Known Activations