© 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. 30749
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "video" and related terms indicating engagement or subscription actions

    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
    152
    +0.10
    0.4%
    307
    +0.10
    0.4%
    139
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.10
    -0.01
    477
    +0.10
    0.01
    28
    +0.09
    0.01
    Negative Logits
    bage
    -0.65
    vantage
    -0.64
     Vanderbilt
    -0.63
    corn
    -0.63
    vale
    -0.62
     Squirrel
    -0.60
     comprom
    -0.60
    rious
    -0.60
    fax
    -0.60
    onite
    -0.59
    POSITIVE LOGITS
    earch
    0.84
    ently
    0.63
    omorphic
    0.62
    ember
    0.62
    thy
    0.61
    uous
    0.61
    /_
    0.59
     hey
    0.58
    lder
    0.58
     largeDownload
    0.57
    Activations Density 0.066%

    No Known Activations