© 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. 11-RES-JB
    11. 20555
    Prev
    Next
    INDEX
    Explanations

    the end of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    sentences that assert a fact or statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    withstanding
    -0.89
    ',"
    -0.83
    VIDIA
    -0.74
    everal
    -0.73
     satell
    -0.72
     confir
    -0.71
     psychiat
    -0.71
     tremend
    -0.70
     pse
    -0.69
     powering
    -0.69
    POSITIVE LOGITS
     Includes
    1.66
     Contains
    1.40
     Also
    1.33
     Requires
    1.30
     Provides
    1.28
     Useful
    1.27
     Allows
    1.27
     Uses
    1.26
     Comes
    1.26
     Available
    1.24
    Activations Density 0.293%

    No Known Activations