© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29316
    Prev
    Next
    INDEX
    Explanations

    words that begin with the letter 's' or are plural nouns

    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
    338
    +0.11
    0.5%
    218
    +0.10
    0.4%
    47
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.04
    545
    +0.10
    0.03
    314
    +0.10
    -0.00
    Negative Logits
     Emin
    -0.73
    ģĸ
    -0.71
     Centauri
    -0.66
     Annotations
    -0.65
     containment
    -0.63
    stood
    -0.63
    ĸļ
    -0.62
     HI
    -0.60
     Pompe
    -0.59
     decoding
    -0.58
    POSITIVE LOGITS
    oul
    1.09
    ick
    1.01
    ouls
    1.01
    ensical
    0.96
    andals
    0.92
    avior
    0.91
    undown
    0.91
    port
    0.90
    unny
    0.90
    ulture
    0.86
    Activations Density 0.303%

    No Known Activations