© 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. 5591
    Prev
    Next
    INDEX
    Explanations

    phrases indicating large-scale societal issues or conflicts

    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
    330
    +0.13
    0.6%
    154
    +0.10
    0.5%
    622
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.13
    0.04
    616
    +0.10
    0.03
    392
    +0.10
    0.03
    Negative Logits
    ICES
    -0.71
    ably
    -0.66
     Cortana
    -0.59
    ILA
    -0.58
    roma
    -0.57
    aldi
    -0.57
    Pal
    -0.57
     Yel
    -0.56
     Fra
    -0.55
     Yelp
    -0.54
    POSITIVE LOGITS
    scale
    1.11
    bodied
    0.98
    Scale
    0.83
    capacity
    0.79
     scale
    0.75
    dollar
    0.73
    arious
    0.71
     scope
    0.70
    pox
    0.70
    tailed
    0.69
    Activations Density 0.113%

    No Known Activations