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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 18845
    Prev
    Next
    INDEX
    Explanations

    phrases related to praising or celebrating

    oai_token-act-pair · gpt-3.5-turbo

    terms that express acclaim or recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascript
    -0.81
     diapers
    -0.79
    omaly
    -0.78
    uyomi
    -0.77
    hing
    -0.77
    thia
    -0.76
     diaper
    -0.71
     captcha
    -0.69
     inhib
    -0.68
     stomach
    -0.68
    POSITIVE LOGITS
     praises
    0.81
     virtues
    0.78
    enance
    0.77
    Supporters
    0.73
     Friedman
    0.71
     hailed
    0.70
    Stand
    0.70
    GROUND
    0.66
     loudly
    0.66
     acclaim
    0.65
    Activations Density 0.041%

    No Known Activations