© 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. 30479
    Prev
    Next
    INDEX
    Explanations

    descriptions of scenic locations and their views

    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
    51
    +0.13
    0.6%
    234
    +0.10
    0.5%
    115
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    596
    +0.13
    0.07
    753
    +0.10
    0.06
    677
    +0.10
    0.07
    Negative Logits
    usercontent
    -0.85
    Issue
    -0.79
    imony
    -0.76
    ensor
    -0.76
    andowski
    -0.75
     deletion
    -0.75
     dstg
    -0.75
    IGN
    -0.73
    wage
    -0.71
     faulty
    -0.70
    POSITIVE LOGITS
     scenic
    1.29
     breathtaking
    1.28
    htaking
    1.17
     scenery
    1.14
     spectacular
    1.13
     attractions
    1.12
     views
    1.12
     overlook
    1.09
     sunset
    1.09
     majestic
    1.07
    Activations Density 2.702%

    No Known Activations