© 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. 10-RES-JB
    11. 3136
    Prev
    Next
    INDEX
    Explanations

    phrases indicating pressure or requests from external sources

    oai_token-act-pair · gpt-3.5-turbo

    the word "from" indicating sources or origins of information

    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
    merce
    -0.83
    hene
    -0.71
    omial
    -0.70
    imate
    -0.68
    mone
    -0.68
    mix
    -0.67
    isode
    -0.66
    nets
    -0.65
    isec
    -0.65
    idy
    -0.65
    POSITIVE LOGITS
     afar
    1.57
     abroad
    1.27
     within
    1.12
     inside
    1.04
     elsewhere
    1.04
     superiors
    1.03
     outside
    1.03
     constituents
    1.01
     outsiders
    0.99
     strangers
    0.93
    Activations Density 0.144%

    No Known Activations