© 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. 32208
    Prev
    Next
    INDEX
    Explanations

    clauses that discuss legal or regulatory changes

    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
    756
    +0.18
    0.9%
    642
    +0.14
    0.7%
    97
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.18
    0.30
    145
    +0.14
    0.24
    440
    +0.13
    0.20
    Negative Logits
    Plot
    -0.84
    Trivia
    -0.83
    âĵĺ
    -0.82
    geries
    -0.76
     âĵĺ
    -0.72
     paranormal
    -0.71
    iour
    -0.71
    BuyableInstoreAndOnline
    -0.70
    DragonMagazine
    -0.70
    odiac
    -0.68
    POSITIVE LOGITS
     Advoc
    1.13
    States
    1.06
    Supporters
    1.04
     legislatures
    1.04
     EFF
    0.97
     States
    0.97
     Legisl
    0.96
     mand
    0.95
     incentiv
    0.95
    TPP
    0.95
    Activations Density 1.868%

    No Known Activations