© 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. 8-RES_POST_32K-OAI
    11. 8063
    Prev
    Next
    INDEX
    Explanations

    phrases indicating age or youth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    615
    +0.11
    0.5%
    381
    +0.11
    0.5%
    445
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.11
    0.11
    362
    +0.11
    0.07
    704
    +0.09
    0.04
    Negative Logits
     Creator
    -0.75
     ///
    -0.69
     attributable
    -0.67
     ISBN
    -0.65
    zsche
    -0.65
     analogous
    -0.63
     SetFontSize
    -0.61
     Balanced
    -0.60
     proportional
    -0.60
     Equ
    -0.59
    POSITIVE LOGITS
     passenger
    0.91
     teenager
    0.81
    flame
    0.81
     hitch
    0.73
     kid
    0.73
     cub
    0.71
    edly
    0.70
    nown
    0.70
    een
    0.69
    fresh
    0.69
    Activations Density 0.451%

    No Known Activations