© 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. 10-RES-JB
    11. 7849
    Prev
    Next
    INDEX
    Explanations

    numbers preceded by apostrophes

    oai_token-act-pair · gpt-3.5-turbo

    negations or words indicating what is not true or should not happen

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     laun
    -0.75
     mortg
    -0.70
     Kirin
    -0.68
     Cinderella
    -0.67
     helicop
    -0.67
     princ
    -0.67
     nomine
    -0.66
     Duo
    -0.58
     Powered
    -0.58
     convol
    -0.56
    POSITIVE LOGITS
    't
    1.58
    aturally
    1.17
    itely
    1.16
    aught
    1.09
    ately
    1.07
    ought
    0.92
    fortunately
    0.91
    omore
    0.90
    ighter
    0.87
    ÃŃ
    0.86
    Activations Density 0.016%

    No Known Activations