© 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. 31229
    Prev
    Next
    INDEX
    Explanations

    elements related to detailed descriptions of events or narratives

    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
    +0.17
    0.8%
    616
    +0.11
    0.5%
    164
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.17
    0.10
    393
    +0.11
    0.11
    528
    +0.10
    0.08
    Negative Logits
    Either
    -0.81
    Enlarge
    -0.80
    ":"/
    -0.77
    \":
    -0.76
    Usually
    -0.76
    Í
    -0.75
    ulum
    -0.75
    itas
    -0.74
    iku
    -0.73
    matter
    -0.73
    POSITIVE LOGITS
     numerous
    0.68
     assorted
    0.67
     newcom
    0.60
     revised
    0.59
     invitations
    0.59
     Numerous
    0.58
     plus
    0.58
     molten
    0.58
     dozens
    0.57
     revamped
    0.57
    Activations Density 1.568%

    No Known Activations