© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5863
    Prev
    Next
    INDEX
    Explanations

    references to exploration or discovery within the context of a broader narrative

    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
    373
    +0.19
    0.9%
    218
    +0.17
    0.8%
    419
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.19
    -0.01
    208
    +0.17
    0.01
    419
    +0.11
    0.01
    Negative Logits
    clair
    -0.78
    yss
    -0.72
     msec
    -0.70
    dates
    -0.69
    apo
    -0.68
    iasm
    -0.64
    currency
    -0.64
    pless
    -0.63
     tongues
    -0.63
     hindsight
    -0.63
    POSITIVE LOGITS
    \\\\\\\\
    0.70
    ä½ľ
    0.67
    Rich
    0.66
     Wyatt
    0.64
     Sph
    0.61
     Cumm
    0.61
    Ħ
    0.59
    biz
    0.57
     Brittany
    0.57
    lor
    0.57
    Activations Density 0.051%

    No Known Activations