© 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. 12940
    Prev
    Next
    INDEX
    Explanations

    terms related to political figures

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and specific substrings that occur frequently in a text

    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
     Cave
    -0.74
    ciating
    -0.68
     Trails
    -0.67
     Cortex
    -0.66
     Maze
    -0.65
    illon
    -0.64
     Finch
    -0.61
    adapt
    -0.61
    ée
    -0.61
     Trail
    -0.59
    POSITIVE LOGITS
    ,,
    2.27
    osi
    1.73
    ofi
    1.56
    ,.
    1.53
    ""
    1.47
    ,,,,
    1.37
    .""
    1.24
    oho
    1.13
    :(
    1.12
     ""
    1.12
    Activations Density 0.060%

    No Known Activations