© 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. 3293
    Prev
    Next
    INDEX
    Explanations

    references to influential figures or entities

    oai_token-act-pair · gpt-3.5-turbo

    the term "leading", particularly in various contexts and its associated phrases

    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
    bley
    -0.71
    atron
    -0.69
    apo
    -0.67
    ships
    -0.66
    bryce
    -0.66
    ilation
    -0.66
    ossession
    -0.65
    ALLY
    -0.64
    cia
    -0.64
    thur
    -0.64
    POSITIVE LOGITS
     scorer
    1.09
     edge
    1.07
     contenders
    1.02
     indicators
    1.01
     contender
    1.01
     indicator
    1.01
     proponent
    0.98
     rusher
    0.90
    stone
    0.86
     exponent
    0.84
    Activations Density 0.032%

    No Known Activations