© 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. 6-RES-JB
    11. 3539
    Prev
    Next
    INDEX
    Explanations

    words related to bodily fluids and waste products

    oai_token-act-pair · gpt-3.5-turbo

    references to urine and related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aido
    -1.06
    ovie
    -0.85
    rals
    -0.82
    asio
    -0.70
    olia
    -0.70
    ertain
    -0.69
    cffffcc
    -0.69
    姫
    -0.69
    pdf
    -0.69
    major
    -0.68
    POSITIVE LOGITS
    ysis
    0.99
    pee
    0.98
     bladder
    0.95
     ejac
    0.92
     urine
    0.89
     stains
    0.88
     metabolites
    0.83
     dripping
    0.79
     soaked
    0.78
     flush
    0.76
    Activations Density 0.060%

    No Known Activations