© 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. 3-RES-JB
    11. 1770
    Prev
    Next
    INDEX
    Explanations

    technical terms related to photography equipment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to camera specifications and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bek
    -0.84
    tale
    -0.73
    CHAT
    -0.72
    isode
    -0.71
    meal
    -0.70
    erous
    -0.67
    pages
    -0.67
    lia
    -0.67
    hern
    -0.67
    mone
    -0.67
    POSITIVE LOGITS
    asonic
    0.85
     Nikon
    0.85
    olt
    0.82
     lenses
    0.81
     aperture
    0.80
     sensitivity
    0.79
     presets
    0.78
    amsung
    0.77
     lens
    0.77
     Leica
    0.76
    Activations Density 0.077%

    No Known Activations