© 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. 11379
    Prev
    Next
    INDEX
    Explanations

    phrases related to involvement or participation in various activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "engage" and its variations in various contexts

    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
    ahon
    -0.67
    pler
    -0.67
     overrun
    -0.63
    dylib
    -0.61
     confir
    -0.56
    DragonMagazine
    -0.56
     Printed
    -0.56
    atto
    -0.55
     scattering
    -0.55
    ough
    -0.55
    POSITIVE LOGITS
    ments
    0.91
    ingly
    0.80
     with
    0.78
     actively
    0.76
    ienced
    0.76
    igate
    0.73
    antically
    0.73
    TAIN
    0.73
    ment
    0.70
     hostilities
    0.70
    Activations Density 0.030%

    No Known Activations