© 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. 27251
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mathematical operations and allocations

    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
    480
    +0.15
    0.7%
    255
    +0.14
    0.7%
    393
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    698
    +0.15
    0.17
    575
    +0.14
    0.16
    255
    +0.10
    0.16
    Negative Logits
    hya
    -0.71
    kef
    -0.64
     advoc
    -0.62
     Ambro
    -0.61
     mathemat
    -0.59
     enthusi
    -0.57
     Devils
    -0.54
     Tuls
    -0.54
    enges
    -0.53
    Management
    -0.53
    POSITIVE LOGITS
     preceding
    0.91
     minus
    0.87
     unchanged
    0.87
    else
    0.85
     thereafter
    0.83
     adjacent
    0.83
     remaining
    0.82
     else
    0.81
    endif
    0.80
     corresponding
    0.78
    Activations Density 2.343%

    No Known Activations