© 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. 5794
    Prev
    Next
    INDEX
    Explanations

    references to specific titles or subjects involving "Ultima."

    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
    503
    +0.10
    0.5%
    311
    +0.10
    0.5%
    284
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.10
    0.01
    116
    +0.10
    0.01
    284
    +0.10
    0.01
    Negative Logits
    keeping
    -0.67
     Passion
    -0.65
     plaque
    -0.62
    ãģĦ
    -0.62
     Candy
    -0.59
     palms
    -0.59
     thumbs
    -0.58
     Pioneer
    -0.57
     hand
    -0.57
     courtesy
    -0.57
    POSITIVE LOGITS
    imates
    1.71
    raviolet
    1.39
    imated
    1.23
    rav
    1.23
    ima
    1.23
    ral
    1.22
    imus
    1.20
    imating
    1.16
    imately
    1.11
    imo
    1.09
    Activations Density 0.045%

    No Known Activations