© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 1923
    Prev
    Next
    INDEX
    Explanations

    words related to mountainous terrain

    oai_token-act-pair · gpt-3.5-turbo

    references to "grotesque" themes and imagery, particularly in relation to social issues or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yuan
    -0.70
     Flavoring
    -0.70
     timet
    -0.67
     Uri
    -0.66
     millenn
    -0.66
    eness
    -0.63
     realization
    -0.63
     ultras
    -0.63
     Apocalypse
    -0.62
     Witnesses
    -0.60
    POSITIVE LOGITS
    mount
    2.35
    flower
    2.33
    gro
    2.33
    weather
    2.07
    blade
    1.64
    pole
    1.63
    horn
    1.59
    mouth
    1.55
    field
    1.54
    wood
    1.53
    Activations Density 0.024%

    No Known Activations