© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 6343
    Prev
    Next
    INDEX
    Explanations

    references to mental health, anxiety, and substance use

    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
    +0.22
    1.0%
    302
    +0.09
    0.4%
    114
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.15
    225
    +0.09
    0.12
    325
    +0.09
    0.11
    Negative Logits
    iversary
    -0.79
    prototype
    -0.75
    rily
    -0.72
    daq
    -0.71
    pheus
    -0.67
    azon
    -0.67
    kefeller
    -0.66
     Pengu
    -0.64
    endum
    -0.63
    abal
    -0.62
    POSITIVE LOGITS
     âĵĺ
    0.98
     (%)
    0.92
    .--
    0.88
     ..........
    0.82
    ¶
    0.81
    .—
    0.78
     âĨ
    0.77
     Increased
    0.77
     âĹı
    0.77
     :
    0.74
    Activations Density 1.903%

    No Known Activations