© 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. 8-RES_POST_32K-OAI
    11. 7755
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals named "Nam" and "Lam."

    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
    187
    +0.15
    0.7%
    739
    +0.13
    0.6%
    124
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.02
    232
    +0.13
    0.02
    740
    +0.10
    0.01
    Negative Logits
     outgoing
    -0.64
     Flickr
    -0.63
     posit
    -0.63
     inference
    -0.62
     textbooks
    -0.61
     cider
    -0.61
    ettings
    -0.60
    ANGE
    -0.59
    DIR
    -0.58
     eyebrow
    -0.58
    POSITIVE LOGITS
    ibia
    1.29
    eless
    1.23
    ankind
    0.99
    pered
    0.97
    ilitary
    0.94
    azing
    0.92
    ilit
    0.92
    essage
    0.90
    aste
    0.89
    ilitation
    0.85
    Activations Density 0.046%

    No Known Activations