© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 28626
    Prev
    Next
    INDEX
    Explanations

    terms related to acknowledgment and identification

    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
    679
    +0.11
    0.5%
    288
    +0.11
    0.5%
    238
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    654
    +0.11
    0.02
    642
    +0.11
    0.02
    431
    +0.10
    0.02
    Negative Logits
    ieri
    -0.82
    olit
    -0.76
     confir
    -0.75
    nz
    -0.72
    ionage
    -0.70
    ework
    -0.70
    ovie
    -0.70
    usterity
    -0.70
    eware
    -0.67
    hell
    -0.65
    POSITIVE LOGITS
    ibly
    0.96
    ledged
    0.87
     landmarks
    0.79
    ances
    0.79
    ably
    0.77
    recogn
    0.74
    ibility
    0.70
     Recogn
    0.69
    ability
    0.68
     handwriting
    0.67
    Activations Density 0.148%

    No Known Activations