© 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. 8-RES-JB
    11. 7104
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions directed towards a specific person

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or character

    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
    ĸļ
    -0.82
    Sense
    -0.67
    ģĸ
    -0.63
     Anger
    -0.63
    SourceFile
    -0.62
    Leaks
    -0.62
     Fulton
    -0.61
    iott
    -0.61
    Share
    -0.60
     Magazine
    -0.60
    POSITIVE LOGITS
     ineligible
    0.96
     elig
    0.95
     abroad
    0.87
     invol
    0.81
     vanquished
    0.79
    atar
    0.72
     onto
    0.72
    subject
    0.71
     unlawfully
    0.71
     willingly
    0.71
    Activations Density 0.170%

    No Known Activations