© 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 EvalsExportsinterp-engineNEWAPI 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. 32086
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols, indicating a focus on non-standard textual elements or encoding

    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
    373
    +0.16
    0.7%
    635
    +0.11
    0.5%
    621
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    254
    +0.16
    0.13
    23
    +0.11
    0.13
    426
    +0.11
    0.10
    Negative Logits
    espie
    -0.81
     Dill
    -0.81
    mort
    -0.66
     Dragonbound
    -0.66
     Telegram
    -0.65
     Donn
    -0.65
     Berm
    -0.63
    weights
    -0.63
     Monsanto
    -0.62
     Daly
    -0.61
    POSITIVE LOGITS
    ŃĶ
    1.36
    Ī
    1.27
    ķ
    1.27
    Ł
    1.27
    Ŀ
    1.27
    ı
    1.26
    ĺ
    1.25
    Ĩ
    1.24
    Ģ
    1.23
    ģ«
    1.23
    Activations Density 1.044%

    No Known Activations