© 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. 10-RES_POST_32K-OAI
    11. 29056
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal endorsements or recommendations, particularly in product reviews

    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
    71
    +0.16
    0.7%
    341
    +0.12
    0.6%
    159
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.16
    0.07
    496
    +0.12
    0.08
    354
    +0.11
    0.06
    Negative Logits
    advertising
    -0.80
    instead
    -0.79
     )]
    -0.75
     ..........
    -0.73
    unknown
    -0.72
    Merit
    -0.71
    don
    -0.70
     nowhere
    -0.69
    livious
    -0.69
    ãĥĺ
    -0.68
    POSITIVE LOGITS
     indeed
    0.78
     technically
    0.70
    ivan
    0.69
     correct
    0.66
     qualifies
    0.65
     theoretically
    0.61
     exist
    0.60
     literal
    0.59
     exists
    0.58
     existed
    0.56
    Activations Density 1.175%

    No Known Activations