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. 0-RES-JB
    6. 19432
    Prev
    Next
    INDEX
    Explanations

    numbers that end with 'dec'

    oai_token-act-pair · gpt-3.5-turbo

    patterns of decline or decrease in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Portal
    -0.69
     Rush
    -0.64
     testers
    -0.63
    *:
    -0.63
     slavery
    -0.62
     Live
    -0.60
     bondage
    -0.60
     apes
    -0.59
    ORPG
    -0.58
     suited
    -0.58
    POSITIVE LOGITS
    dec
    4.00
    Dec
    1.73
     Dec
    1.64
    DEC
    1.57
     dec
    1.52
     DEC
    1.47
    oct
    1.31
    deb
    1.20
    incre
    1.18
    century
    1.15
    Activations Density 0.009%

    No Known Activations