© 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. 6333
    Prev
    Next
    INDEX
    Explanations

    topics related to environmental issues or health concerns

    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
    256
    +0.11
    0.5%
    591
    +0.11
    0.5%
    428
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.11
    0.23
    94
    +0.11
    0.16
    615
    +0.10
    0.14
    Negative Logits
    âĶĢâĶĢâĶĢâĶĢ
    -0.84
    Lago
    -0.78
    REDACTED
    -0.76
    emort
    -0.72
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.71
    «
    -0.71
    lvl
    -0.70
    plot
    -0.69
    priority
    -0.69
    $$
    -0.68
    POSITIVE LOGITS
    SPONSORED
    0.81
     Shutterstock
    0.78
    Companies
    0.76
     Pew
    0.74
     outbreaks
    0.74
     researcher
    0.73
     Mash
    0.71
     Lena
    0.71
     NPR
    0.71
     VICE
    0.70
    Activations Density 0.933%

    No Known Activations