© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11029
    Prev
    Next
    INDEX
    Explanations

    text related to the messaging platform "WhatsApp"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "Whats" or "what's"

    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
    ³³³
    -0.77
     differential
    -0.75
    CVE
    -0.66
    eers
    -0.65
    eering
    -0.63
     Roh
    -0.63
     Franch
    -0.62
     compens
    -0.61
     demolition
    -0.60
     Crus
    -0.59
    POSITIVE LOGITS
    app
    1.11
    ocial
    1.05
    bour
    1.00
    App
    0.99
    omething
    0.96
    iques
    0.92
    creen
    0.89
    ername
    0.86
    alon
    0.84
    peed
    0.82
    Activations Density 0.024%

    No Known Activations