© 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. 27896
    Prev
    Next
    INDEX
    Explanations

    mentions of pollution and related terms

    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
    314
    +0.16
    0.7%
    490
    +0.11
    0.5%
    689
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    698
    +0.16
    0.02
    490
    +0.11
    0.02
    144
    +0.09
    0.01
    Negative Logits
     Flavoring
    -0.82
     Melody
    -0.68
     Ashe
    -0.63
     Revel
    -0.63
    ALLY
    -0.63
    MpServer
    -0.62
     Journey
    -0.61
     GSL
    -0.61
     Bold
    -0.61
     ultraviolet
    -0.61
    POSITIVE LOGITS
    uting
    1.44
    uters
    1.38
    uter
    1.37
    uted
    1.37
    inators
    1.35
    ution
    1.34
    utions
    1.22
    inator
    1.22
    ination
    1.17
    inating
    1.12
    Activations Density 0.061%

    No Known Activations