© 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. 20164
    Prev
    Next
    INDEX
    Explanations

    words related to bathroom fixtures

    oai_token-act-pair · gpt-3.5-turbo

    references to toilets and related plumbing topics

    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
    )=(
    -0.72
     forth
    -0.68
    */(
    -0.68
    REDACTED
    -0.67
    CVE
    -0.67
    adena
    -0.67
    udic
    -0.66
    eq
    -0.63
     Anarchy
    -0.63
    ozy
    -0.63
    POSITIVE LOGITS
     plun
    0.95
     cleaner
    0.91
     bowl
    0.89
     toilets
    0.88
    ysis
    0.84
    bowl
    0.84
     cleaners
    0.81
     toilet
    0.81
     bowls
    0.77
    washer
    0.77
    Activations Density 0.044%

    No Known Activations