Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 24260
    Prev
    Next
    INDEX
    Explanations

    instances of tear-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to tears and tear-related emotions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eton
    -0.72
    enhagen
    -0.72
    abilities
    -0.72
    ioned
    -0.68
    ITNESS
    -0.68
    zsche
    -0.67
    alty
    -0.67
    POL
    -0.66
    Û
    -0.66
    REDACTED
    -0.66
    POSITIVE LOGITS
    adoes
    1.11
    ful
    1.09
    fully
    0.96
     duct
    0.93
    bows
    0.92
    gas
    0.89
    stained
    0.88
    fulness
    0.88
    ados
    0.88
    adic
    0.86
    Activations Density 0.047%

    No Known Activations