© 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. 8-RES-JB
    11. 7627
    Prev
    Next
    INDEX
    Explanations

    references to places or objects related to the word "Bath."

    oai_token-act-pair · gpt-3.5-turbo

    references to bathing and bath-related products or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Publisher
    -0.66
    andum
    -0.65
    arily
    -0.64
     Uruguay
    -0.64
    NING
    -0.63
     Collider
    -0.63
     srf
    -0.61
     Kers
    -0.61
     Reaper
    -0.60
    vernment
    -0.60
    POSITIVE LOGITS
    tub
    1.89
    urst
    1.46
    robe
    1.34
    room
    1.31
    rooms
    1.31
    water
    1.09
     salts
    0.99
    she
    0.96
    bath
    0.94
    house
    0.88
    Activations Density 0.037%

    No Known Activations