© 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. 30124
    Prev
    Next
    INDEX
    Explanations

    expressions indicating effectiveness or efficacy

    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
    478
    +0.11
    0.5%
    392
    +0.10
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.02
    555
    +0.10
    0.01
    314
    +0.10
    0.00
    Negative Logits
    ²¾
    -0.77
     oath
    -0.74
    Downloadha
    -0.68
     guiActiveUnfocused
    -0.67
     Remastered
    -0.67
    kees
    -0.66
     Journals
    -0.64
    channelAvailability
    -0.64
    BuyableInstoreAndOnline
    -0.64
    ciating
    -0.63
    POSITIVE LOGITS
    orts
    1.43
    luent
    1.39
    erves
    1.30
    emin
    1.20
    usive
    1.19
    usion
    1.18
    ort
    1.17
    endi
    1.17
    acement
    1.14
    luence
    1.12
    Activations Density 0.054%

    No Known Activations