© 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. 29931
    Prev
    Next
    INDEX
    Explanations

    figurative expressions related to pressure and tension

    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
    164
    +0.11
    0.5%
    258
    +0.11
    0.5%
    324
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.11
    0.17
    377
    +0.11
    0.15
    737
    +0.09
    0.11
    Negative Logits
    Sah
    -0.72
    ãĥ´ãĤ¡
    -0.70
    ãĥĺãĥ©
    -0.67
    ãĥ¼ãĥĨãĤ£
    -0.67
    Beta
    -0.64
    yond
    -0.64
     horm
    -0.63
    ipl
    -0.62
    endar
    -0.62
    arov
    -0.61
    POSITIVE LOGITS
     financially
    0.97
     offensively
    0.85
     academ
    0.82
     economically
    0.75
     athlet
    0.74
     elector
    0.73
     defensively
    0.70
     politically
    0.70
     diplom
    0.67
    enance
    0.66
    Activations Density 2.716%

    No Known Activations