© 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. 2-RES-JB
    11. 7529
    Prev
    Next
    INDEX
    Explanations

    instances where rewriting or reworking something is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of rewriting or alterations made to various texts or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ells
    -0.76
     Charity
    -0.73
    ello
    -0.71
    spot
    -0.67
    amina
    -0.67
    regate
    -0.66
    ¬¼
    -0.65
     Charm
    -0.65
    Bar
    -0.63
     Anthem
    -0.62
    POSITIVE LOGITS
     rewrite
    1.34
     rewritten
    1.24
     rewriting
    1.16
     restruct
    0.89
     rethink
    0.85
     raping
    0.75
     reorgan
    0.72
    dated
    0.72
     cram
    0.70
    é»Ĵ
    0.69
    Activations Density 0.017%

    No Known Activations