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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 6883
    Prev
    Next
    INDEX
    Explanations

    references to activities or objects related to taking a bath

    oai_token-act-pair · gpt-3.5-turbo

    mentions of baths and bathing activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     srf
    -0.70
    infeld
    -0.68
    phis
    -0.68
     ubiquitous
    -0.65
     thriving
    -0.62
    axies
    -0.62
    guided
    -0.61
     disparate
    -0.61
     inevitable
    -0.61
    seless
    -0.61
    POSITIVE LOGITS
    tub
    1.67
    robe
    1.08
     baths
    1.07
    room
    1.02
    rooms
    0.98
     tub
    0.98
    urst
    0.97
     ashore
    0.92
     bath
    0.92
     salts
    0.90
    Activations Density 0.008%

    No Known Activations