© 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. 8-RES_POST_32K-OAI
    6. 5660
    Prev
    Next
    INDEX
    Explanations

    terms related to livestock, particularly sheep and cattle

    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
    347
    +0.13
    0.6%
    583
    +0.11
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.03
    99
    +0.11
    0.02
    350
    +0.10
    0.02
    Negative Logits
    uyomi
    -0.76
     unlaw
    -0.71
     validity
    -0.69
     Fiction
    -0.68
     Bleach
    -0.63
     Genius
    -0.63
     Crom
    -0.62
     demolition
    -0.62
     subsequ
    -0.60
     GDDR
    -0.60
    POSITIVE LOGITS
     grazing
    1.03
     pasture
    0.97
    yard
    0.93
     graz
    0.91
    folk
    0.89
    skin
    0.89
    aughtered
    0.89
     goats
    0.88
     ranc
    0.87
     gra
    0.85
    Activations Density 0.079%

    No Known Activations