© 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. 10-RES-JB
    6. 7054
    Prev
    Next
    INDEX
    Explanations

    mentions of places or concepts named "Sin"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Sin" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enance
    -0.78
    è¦ļéĨĴ
    -0.75
    ITAL
    -0.72
    berman
    -0.63
     attainment
    -0.62
     Mellon
    -0.60
     NAD
    -0.59
     CONTIN
    -0.59
    ski
    -0.59
    inately
    -0.58
    POSITIVE LOGITS
    atra
    1.37
    clair
    1.30
    ners
    1.23
    ister
    1.11
    ews
    1.10
    estro
    1.07
    ew
    1.05
    uous
    1.05
    ned
    0.99
    fully
    0.94
    Activations Density 0.028%

    No Known Activations