© 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 EvalsExportsinterp-engineNEWAPI 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. 32582
    Prev
    Next
    INDEX
    Explanations

    references to natural landscapes and geographical features

    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
    644
    +0.13
    0.6%
    7
    +0.10
    0.5%
    55
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.08
    537
    +0.10
    0.06
    377
    +0.10
    0.07
    Negative Logits
    ASED
    -0.65
    otide
    -0.65
    LEASE
    -0.65
     Unloaded
    -0.64
     copyrighted
    -0.63
     faulty
    -0.62
    arus
    -0.62
     defective
    -0.62
    rators
    -0.61
    ANN
    -0.60
    POSITIVE LOGITS
    ide
    1.23
    cape
    1.04
     surrounding
    1.00
    ides
    0.97
     west
    0.89
    outheast
    0.84
     northeast
    0.84
     east
    0.82
     northwest
    0.82
    cale
    0.79
    Activations Density 0.750%

    No Known Activations