© 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. 6069
    Prev
    Next
    INDEX
    Explanations

    scientific observations and findings related to planetary atmospheres and their properties

    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
    7
    +0.10
    0.5%
    463
    +0.10
    0.4%
    705
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.10
    -0.07
    724
    +0.10
    0.21
    7
    +0.09
    0.14
    Negative Logits
    iquette
    -0.88
     Homeless
    -0.88
     Streets
    -0.83
     Restaur
    -0.81
    Exit
    -0.79
     Voters
    -0.77
     Corker
    -0.74
    street
    -0.74
     Rivals
    -0.73
     Sons
    -0.71
    POSITIVE LOGITS
     scientists
    1.48
     physicists
    1.44
     scientific
    1.38
    Scientists
    1.33
     biologists
    1.31
     computational
    1.27
     scientifically
    1.23
     molecular
    1.21
    scient
    1.20
     Scientists
    1.20
    Activations Density 7.654%

    No Known Activations