© 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. 7570
    Prev
    Next
    INDEX
    Explanations

    proper names

    oai_token-act-pair · gpt-3.5-turbo

    the name "Roy"

    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
     negatives
    -0.69
     Sorceress
    -0.68
     cascade
    -0.67
     overload
    -0.66
     FML
    -0.64
     nonexistent
    -0.63
     multipl
    -0.62
     func
    -0.62
     inputs
    -0.61
     cluster
    -0.60
    POSITIVE LOGITS
    roy
    4.83
    Royal
    1.38
    Roy
    1.32
    roit
    1.17
    oy
    1.11
    roe
    1.07
     Troy
    1.06
    rey
    1.06
    rea
    1.03
    rib
    1.03
    Activations Density 0.015%

    No Known Activations