© 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. 30033
    Prev
    Next
    INDEX
    Explanations

    terms related to "hood" or hoods in various 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
    701
    +0.11
    0.5%
    592
    +0.11
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.03
    701
    +0.11
    0.01
    326
    +0.10
    0.02
    Negative Logits
     Lauder
    -0.91
    lihood
    -0.70
    nces
    -0.69
    tery
    -0.67
    ×ķ
    -0.63
     AVG
    -0.63
    TABLE
    -0.63
    ngth
    -0.63
    MENT
    -0.63
     Gaul
    -0.59
    POSITIVE LOGITS
    ie
    1.31
    oos
    1.16
    ed
    1.16
    ies
    1.08
    oo
    1.02
    edo
    0.94
    tip
    0.94
    ier
    0.93
    ied
    0.89
     ornament
    0.89
    Activations Density 0.158%

    No Known Activations