© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 29745
    Prev
    Next
    INDEX
    Explanations

    indicators of psychological assessments and scores related to mental health

    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
    495
    +0.10
    0.5%
    307
    +0.10
    0.4%
    378
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.10
    0.05
    6
    +0.10
    0.09
    369
    +0.09
    0.05
    Negative Logits
     --
    -1.17
    ..."
    -0.99
    ...?
    -0.96
     "...
    -0.93
    ...)
    -0.92
    ...
    -0.91
     ...
    -0.88
    "...
    -0.86
     ..."
    -0.83
     ``
    -0.82
    POSITIVE LOGITS
     âĪĴ
    2.39
    âĪĴ
    1.80
    âĢIJ
    1.79
     ÂŃ
    1.76
     (âĪĴ
    1.66
    âĢij
    1.42
    ·
    1.36
     âĪ¼
    1.15
     β
    1.10
    ³³³³³³³³
    1.08
    Activations Density 2.312%

    No Known Activations