© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 10303
    Prev
    Next
    INDEX
    Explanations

    texts related to redesign or restructure

    oai_token-act-pair · gpt-3.5-turbo

    terms related to changes and improvements in design or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Examiner
    -0.72
     Charity
    -0.71
    ulhu
    -0.70
    Ver
    -0.67
     Planes
    -0.66
    Church
    -0.65
    Pa
    -0.65
     charism
    -0.64
    Yu
    -0.62
     Ing
    -0.62
    POSITIVE LOGITS
     redesign
    1.22
     redesigned
    1.04
     reinvent
    0.96
     rethink
    0.96
     redef
    0.95
     rewrite
    0.85
     refreshed
    0.84
     revamped
    0.84
     restruct
    0.83
    inition
    0.82
    Activations Density 0.021%

    No Known Activations