© 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. 26705
    Prev
    Next
    INDEX
    Explanations

    phrases indicating outcomes or consequences

    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
    314
    +0.12
    0.6%
    334
    +0.10
    0.5%
    761
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    689
    +0.12
    0.03
    761
    +0.10
    0.03
    201
    +0.10
    0.03
    Negative Logits
    tsky
    -0.76
    theless
    -0.59
     beds
    -0.58
     Talking
    -0.58
     deed
    -0.56
     spaced
    -0.54
     crept
    -0.53
     Chili
    -0.53
     Doctrine
    -0.53
    flo
    -0.53
    POSITIVE LOGITS
    antly
    0.84
    igate
    0.76
    inally
    0.74
    aneously
    0.72
     primarily
    0.72
     solely
    0.71
    âĹ¼
    0.69
    gest
    0.69
    iate
    0.69
    otally
    0.68
    Activations Density 0.117%

    No Known Activations