© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 26974
    Prev
    Next
    INDEX
    Explanations

    concepts related to consumer rights and refunds

    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
    702
    +0.09
    0.4%
    560
    +0.09
    0.4%
    279
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    279
    +0.09
    0.08
    508
    +0.09
    0.06
    646
    +0.09
    0.05
    Negative Logits
    NetMessage
    -0.74
     Murd
    -0.73
     taboo
    -0.67
     horr
    -0.66
    olina
    -0.65
     symbolism
    -0.65
     extravag
    -0.65
    illion
    -0.65
    bryce
    -0.64
    roots
    -0.64
    POSITIVE LOGITS
     refunds
    1.28
     notification
    1.27
     refund
    1.21
     notified
    1.19
     informed
    1.17
     timely
    1.17
     notice
    1.15
     notices
    1.15
     updates
    1.10
     assurance
    1.09
    Activations Density 1.064%

    No Known Activations