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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 1080
    Prev
    Next
    INDEX
    Explanations

    names of political figures and entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or characters, particularly those with initials or single-letter identifiers

    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
    SOURCE
    -0.73
    Trust
    -0.66
     Beacon
    -0.65
    ablishment
    -0.65
    Atlantic
    -0.65
    FontSize
    -0.64
     Mercury
    -0.63
     Niagara
    -0.63
     Connie
    -0.62
    Times
    -0.62
    POSITIVE LOGITS
    oub
    1.02
    ollah
    0.88
    abis
    0.88
    utsch
    0.86
    ĪĴ
    0.84
    inav
    0.84
    hai
    0.80
    akh
    0.80
    ymes
    0.80
    agh
    0.80
    Activations Density 0.142%

    No Known Activations