© 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. 10-RES_POST_32K-OAI
    6. 30006
    Prev
    Next
    INDEX
    Explanations

    references and citations in the text

    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
    727
    +0.12
    0.6%
    311
    +0.10
    0.5%
    645
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.02
    311
    +0.10
    0.01
    641
    +0.10
    0.02
    Negative Logits
    ciating
    -0.85
    daq
    -0.71
    NING
    -0.65
    ±
    -0.65
    matically
    -0.62
     Quarterly
    -0.60
     Interstellar
    -0.60
    ITIES
    -0.60
    strument
    -0.60
     atmosphere
    -0.59
    POSITIVE LOGITS
    riger
    1.46
    lections
    1.45
    lection
    1.40
    lected
    1.38
    resh
    1.38
    lect
    1.32
    eren
    1.30
    eree
    1.28
    inery
    1.28
    usal
    1.27
    Activations Density 0.071%

    No Known Activations