© 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. 6508
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning colleagues or companions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "fellow" or similar terms indicating a sense of companionship or camaraderie

    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
    uilt
    -0.68
    rative
    -0.67
    afort
    -0.65
    cise
    -0.64
    _-
    -0.64
    dyl
    -0.63
    inyl
    -0.63
    ossession
    -0.63
    Specific
    -0.63
    uzzle
    -0.62
    POSITIVE LOGITS
     travelers
    1.17
     traveler
    1.12
     travellers
    1.12
     classmates
    1.03
     strugg
    1.02
     traveller
    0.96
    worldly
    0.95
     inmates
    0.87
     citizens
    0.85
     passengers
    0.84
    Activations Density 0.059%

    No Known Activations