© 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. 9-RES-JB
    11. 9872
    Prev
    Next
    INDEX
    Explanations

    phrases related to political involvement and activism

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "em"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     redistributed
    -0.70
     otherwise
    -0.69
    SourceFile
    -0.62
     bed
    -0.58
     dreaded
    -0.56
     enriched
    -0.56
     tipped
    -0.56
     Kubrick
    -0.56
     hel
    -0.54
     heaviest
    -0.54
    POSITIVE LOGITS
    achine
    1.23
    peror
    1.18
    issions
    1.15
    useum
    1.12
    poral
    1.09
    erald
    1.08
    otional
    1.08
    bourg
    1.08
    essage
    1.06
    blance
    1.06
    Activations Density 0.035%

    No Known Activations