© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 22485
    Prev
    Next
    INDEX
    Explanations

    mentions of delegates in a political context

    oai_token-act-pair · gpt-3.5-turbo

    references to political delegates and their dynamics

    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
     times
    -0.70
     quote
    -0.68
     slide
    -0.68
     exp
    -0.67
     crack
    -0.66
     Lit
    -0.66
     tram
    -0.65
     cracks
    -0.64
     cracking
    -0.64
     tim
    -0.62
    POSITIVE LOGITS
    legates
    3.71
    legate
    2.91
     Blasio
    2.12
    olls
    1.44
    leground
    1.40
    cember
    1.07
    letes
    1.07
    ledged
    1.05
    merce
    1.03
    ploy
    1.01
    Activations Density 0.014%

    No Known Activations