© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 18678
    Prev
    Next
    INDEX
    Explanations

    mentions of activities or items related to bathing

    oai_token-act-pair · gpt-3.5-turbo

    references to baths and bathing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     srf
    -0.64
     detriment
    -0.64
    guided
    -0.64
     relegated
    -0.63
    seless
    -0.62
     belief
    -0.62
    support
    -0.60
     rudimentary
    -0.60
     vague
    -0.59
     illeg
    -0.59
    POSITIVE LOGITS
    tub
    1.41
    bath
    1.27
     baths
    0.99
    room
    0.94
     ashore
    0.94
     bath
    0.91
     salts
    0.87
    ouse
    0.86
    urst
    0.86
    rooms
    0.84
    Activations Density 0.010%

    No Known Activations