© 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. 10-RES_POST_32K-OAI
    11. 29598
    Prev
    Next
    INDEX
    Explanations

    references to military technology and gaming influence within modern contexts

    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
    415
    +0.15
    0.7%
    646
    +0.11
    0.5%
    595
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.15
    0.16
    415
    +0.11
    0.14
    575
    +0.11
    0.15
    Negative Logits
     Applicant
    -0.74
     cannabin
    -0.73
    rawdownloadcloneembedreportprint
    -0.72
    ":[{"
    -0.66
    natureconservancy
    -0.65
    east
    -0.64
     acknow
    -0.64
     inexper
    -0.64
    NRS
    -0.62
     Username
    -0.62
    POSITIVE LOGITS
     everywhere
    0.91
     instead
    0.86
    instead
    0.83
    worms
    0.82
     popping
    0.80
     abound
    0.79
     laced
    0.78
    rupulous
    0.77
    icles
    0.76
    bars
    0.75
    Activations Density 2.436%

    No Known Activations