© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29542
    Prev
    Next
    INDEX
    Explanations

    elements related to numbers, references, and formal documentation

    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
    +0.14
    0.6%
    173
    +0.11
    0.5%
    701
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.14
    -0.02
    334
    +0.11
    0.01
    314
    +0.10
    -0.01
    Negative Logits
    bach
    -0.80
    tsky
    -0.78
    heit
    -0.72
    tein
    -0.71
    rosso
    -0.71
    kay
    -0.67
    theless
    -0.66
    ULAR
    -0.65
    lehem
    -0.65
    bats
    -0.64
    POSITIVE LOGITS
     effective
    0.94
     emer
    0.67
     stimulating
    0.67
     affecting
    0.67
     insol
    0.64
     actionGroup
    0.61
     enforcing
    0.60
     Effective
    0.59
     bursting
    0.59
     empowering
    0.59
    Activations Density 0.088%

    No Known Activations