© 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. 11-RES-JB
    11. 20641
    Prev
    Next
    INDEX
    Explanations

    phrases related to commands, warnings, and instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express certainty or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icio
    -0.56
    artney
    -0.55
    arlane
    -0.54
    ibaba
    -0.52
    76561
    -0.50
    yip
    -0.50
    20439
    -0.49
    ento
    -0.49
    yrinth
    -0.49
    uggest
    -0.49
    POSITIVE LOGITS
    !
    1.36
    !:
    1.33
    !.
    1.29
     ;)
    1.23
    !!!
    1.20
    .:
    1.19
     ðŁĻĤ
    1.18
     :)
    1.17
    !!!!
    1.17
    !,
    1.17
    Activations Density 0.737%

    No Known Activations