© 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. 31310
    Prev
    Next
    INDEX
    Explanations

    terms related to dimensions and measurements

    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
    688
    +0.12
    0.5%
    441
    +0.10
    0.5%
    7
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.12
    0.01
    288
    +0.10
    0.02
    503
    +0.10
    0.01
    Negative Logits
    vine
    -0.80
    ciating
    -0.79
    CRIP
    -0.74
    NetMessage
    -0.72
    breakers
    -0.68
    hips
    -0.66
    Desk
    -0.65
    lean
    -0.64
     Royale
    -0.63
    Interstitial
    -0.63
    POSITIVE LOGITS
    ensions
    1.50
    itri
    1.45
    inished
    1.37
    ension
    1.34
    ethy
    1.24
    orph
    1.19
    ention
    1.04
    ethyl
    1.02
    ples
    1.01
    anche
    1.01
    Activations Density 0.100%

    No Known Activations