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. 6-RES-JB
    6. 1853
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to crying

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cry" and its variations in various 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
    awaru
    -0.77
    ajo
    -0.73
    velength
    -0.71
    ratulations
    -0.71
    eties
    -0.70
     nomine
    -0.66
    ulty
    -0.66
    ositories
    -0.66
    ammy
    -0.65
    MG
    -0.65
    POSITIVE LOGITS
    stals
    1.27
    sis
    1.03
    baby
    1.02
    ogen
    0.99
    stall
    0.96
    pter
    0.95
    stal
    0.94
    ogenic
    0.88
    hovah
    0.84
     cry
    0.84
    Activations Density 0.015%

    No Known Activations