© 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. 27054
    Prev
    Next
    INDEX
    Explanations

    variants of the word "new."

    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
    464
    +0.12
    0.5%
    121
    +0.11
    0.5%
    357
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.02
    659
    +0.11
    0.02
    314
    +0.10
    -0.00
    Negative Logits
     depreciation
    -0.63
     misunder
    -0.59
     gam
    -0.58
    ItemTracker
    -0.58
     suspic
    -0.57
    cific
    -0.57
     Monteneg
    -0.56
     apologies
    -0.56
     Polit
    -0.56
     Bravo
    -0.55
    POSITIVE LOGITS
    flies
    0.96
    een
    0.94
    paper
    0.88
    papers
    0.84
    eye
    0.84
    alker
    0.83
    icz
    0.83
    spl
    0.80
    eh
    0.80
    zel
    0.79
    Activations Density 0.128%

    No Known Activations