© 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. 0-RES-JB
    11. 15836
    Prev
    Next
    INDEX
    Explanations

    prices with currency symbols

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'L' in various contexts

    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
     Pax
    -0.61
     turf
    -0.60
     sensational
    -0.58
     roundup
    -0.58
     rolling
    -0.58
     topp
    -0.57
     racket
    -0.56
     untold
    -0.56
     sund
    -0.55
     bouncing
    -0.55
    POSITIVE LOGITS
    L
    3.34
    LR
    1.79
     L
    1.76
    LO
    1.74
    l
    1.73
    LM
    1.70
    LP
    1.67
    LI
    1.66
    LB
    1.64
    LA
    1.63
    Activations Density 0.026%

    No Known Activations