© 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. 10-RES-JB
    11. 5655
    Prev
    Next
    INDEX
    Explanations

    mentions of geopolitical events and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and other linking words that connect phrases or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itas
    -0.69
    apps
    -0.66
    Except
    -0.66
    arse
    -0.65
    ires
    -0.65
    î
    -0.64
    ctors
    -0.64
    ÙIJ
    -0.64
    iors
    -0.63
    Science
    -0.63
    POSITIVE LOGITS
     subsequent
    1.50
     consequ
    1.39
     ensuing
    1.37
     resultant
    1.30
     impending
    1.07
     ongoing
    1.02
     refusal
    1.02
     unwillingness
    1.01
     revelations
    1.00
     lack
    1.00
    Activations Density 0.332%

    No Known Activations