© 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. 1-RES-JB
    11. 2509
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically related to books, authors, and media

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names and terms related to media and fictional works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pher
    -0.87
    onso
    -0.81
    grades
    -0.79
    oney
    -0.76
    frog
    -0.76
    ouse
    -0.76
    bestos
    -0.73
    hops
    -0.71
    onse
    -0.70
    ranged
    -0.66
    POSITIVE LOGITS
    mire
    0.86
     Predator
    0.83
     Conan
    0.81
    agate
    0.74
     precon
    0.72
     Hannity
    0.70
     Syndicate
    0.70
     Zin
    0.69
    aughs
    0.69
     Carlson
    0.68
    Activations Density 0.027%

    No Known Activations