© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 22503
    Prev
    Next
    INDEX
    Explanations

    keywords related to going inside or within something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Inside" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eday
    -0.78
    yah
    -0.76
    olk
    -0.75
    opter
    -0.74
    ron
    -0.71
    enegger
    -0.68
    aler
    -0.68
    uct
    -0.68
    fortune
    -0.68
    eg
    -0.68
    POSITIVE LOGITS
     parentheses
    0.80
     workings
    0.75
    vert
    0.72
     bedrooms
    0.68
     walls
    0.66
     Mansion
    0.65
     Yosemite
    0.65
     latex
    0.64
     chambers
    0.64
     Marble
    0.63
    Activations Density 0.031%

    No Known Activations