© 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. 10718
    Prev
    Next
    INDEX
    Explanations

    numerical examples or illustrations in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "for example" and related expressions

    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
    resy
    -0.72
    ibly
    -0.68
    ses
    -0.66
    sth
    -0.64
    ailable
    -0.64
    lied
    -0.63
    IBLE
    -0.63
    aith
    -0.62
    ima
    -0.61
    Done
    -0.61
    POSITIVE LOGITS
     suppose
    1.28
     imagine
    1.07
     consider
    1.00
     if
    0.98
     Suppose
    0.89
     whereas
    0.89
     although
    0.88
     according
    0.81
     when
    0.78
     compare
    0.77
    Activations Density 0.128%

    No Known Activations