© 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. 13860
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific groups or objects, particularly focusing on concepts that may require defending or addressing activism

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to groups or categories of living beings or entities

    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
    Fla
    -0.71
    iHUD
    -0.70
    tains
    -0.70
     Pars
    -0.64
    amaz
    -0.63
    Ore
    -0.63
    rawdownloadcloneembedreportprint
    -0.61
    Closure
    -0.60
    FG
    -0.60
    aila
    -0.60
    POSITIVE LOGITS
     aren
    1.38
     tend
    1.37
     are
    1.31
     rarely
    1.23
     cannot
    1.22
     prefer
    1.22
     seldom
    1.22
     tended
    1.14
     thrive
    1.14
     differ
    1.14
    Activations Density 0.500%

    No Known Activations