© 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. 0-RES-JB
    11. 11398
    Prev
    Next
    INDEX
    Explanations

    names of a specific individual, "Ellis"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dial
    -0.68
    united
    -0.68
    wheel
    -0.67
     lapt
    -0.66
    LOAD
    -0.66
    Balt
    -0.66
     Mald
    -0.65
     mand
    -0.65
     cou
    -0.65
     mog
    -0.65
    POSITIVE LOGITS
     Ellis
    2.76
     Levi
    1.58
     Isaac
    1.28
     Cullen
    1.13
     Mercer
    1.07
     Spl
    1.04
     Rebecca
    1.03
     Marin
    1.02
     Solomon
    0.97
     Arc
    0.96
    Activations Density 0.031%

    No Known Activations