© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES_POST_32K-OAI
    11. 4493
    Prev
    Next
    INDEX
    Explanations

    instances of the word "iss" and its variations, indicating a focus on issues, concerns, or matters being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    373
    +0.14
    0.7%
    679
    +0.10
    0.5%
    744
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    9
    +0.14
    0.02
    289
    +0.10
    0.01
    152
    +0.10
    0.02
    Negative Logits
    illac
    -0.70
    thens
    -0.69
    bably
    -0.68
     Recall
    -0.68
    phrine
    -0.62
    vised
    -0.61
    thia
    -0.61
    thening
    -0.61
    razil
    -0.60
    shaw
    -0.60
    POSITIVE LOGITS
    ippi
    1.23
    andra
    1.04
    imo
    1.02
    auga
    0.97
    imum
    0.96
    ima
    0.93
    olution
    0.90
    imus
    0.90
    enger
    0.89
    ilon
    0.87
    Activations Density 0.046%

    No Known Activations