© 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. 28096
    Prev
    Next
    INDEX
    Explanations

    timestamps or time-related data

    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
    +0.19
    0.9%
    732
    +0.12
    0.5%
    550
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.19
    0.07
    501
    +0.12
    0.07
    455
    +0.10
    0.07
    Negative Logits
     Lal
    -0.65
    æ©
    -0.64
     Ame
    -0.61
     Canaan
    -0.61
     Kard
    -0.59
     Lethal
    -0.58
    lier
    -0.58
     Mahjong
    -0.56
     Colon
    -0.54
     Angry
    -0.54
    POSITIVE LOGITS
     Logged
    0.77
    bj
    0.70
    '/
    0.69
    addock
    0.68
    iasis
    0.67
    detail
    0.66
    widget
    0.65
    poll
    0.65
    SPONSORED
    0.64
    nos
    0.64
    Activations Density 1.212%

    No Known Activations