© 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. 32451
    Prev
    Next
    INDEX
    Explanations

    emphasized numerical values in the text

    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
    86
    +0.11
    0.5%
    502
    +0.11
    0.5%
    487
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.11
    0.09
    512
    +0.11
    0.07
    96
    +0.10
    0.06
    Negative Logits
    bris
    -0.69
    IAS
    -0.64
    nard
    -0.63
    nes
    -0.61
     Ent
    -0.61
    ourt
    -0.61
     forth
    -0.60
     lashes
    -0.58
    mort
    -0.58
    AIR
    -0.57
    POSITIVE LOGITS
    200
    1.10
    300
    1.02
    050
    0.99
    800
    0.98
    700
    0.97
    600
    0.97
    500
    0.96
    400
    0.96
    100
    0.96
    024
    0.95
    Activations Density 0.246%

    No Known Activations