© 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. 11600
    Prev
    Next
    INDEX
    Explanations

    the superlative or ordinal form of words

    oai_token-act-pair · gpt-3.5-turbo

    indications of notable achievements or significant events

    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
     presently
    -0.88
    INGTON
    -0.79
     Currently
    -0.75
     currently
    -0.70
    Currently
    -0.69
     hereby
    -0.68
    currently
    -0.67
    cgi
    -0.66
    ologies
    -0.65
    ony
    -0.65
    POSITIVE LOGITS
     catalyst
    1.20
     inspiration
    1.11
     impetus
    1.10
     instrumental
    1.05
     memorable
    1.02
     unsuccessful
    1.00
     standout
    0.98
     surprise
    0.97
     fateful
    0.97
     revelation
    0.93
    Activations Density 0.298%

    No Known Activations