© 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. 28653
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and construction activities

    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
    459
    +0.11
    0.5%
    531
    +0.11
    0.5%
    62
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    531
    +0.11
    0.14
    459
    +0.11
    0.07
    274
    +0.11
    0.08
    Negative Logits
    eous
    -0.71
    Reviewer
    -0.69
    bnb
    -0.60
     derog
    -0.58
    endment
    -0.56
     cultivation
    -0.56
     temptation
    -0.56
    ugal
    -0.56
    eq
    -0.56
    dit
    -0.55
    POSITIVE LOGITS
     commenced
    1.33
     took
    1.29
     occurred
    1.22
     commence
    1.20
     started
    1.19
     begun
    1.19
     taking
    1.18
     underway
    1.17
     began
    1.16
     takes
    1.14
    Activations Density 4.840%

    No Known Activations