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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-RES-JB
    6. 14628
    Prev
    Next
    INDEX
    Explanations

    words related to speed, growth, and change

    oai_token-act-pair · gpt-3.5-turbo

    phrases or statistics related to rates of occurrence or measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.93
    IRT
    -0.82
    enegger
    -0.74
    ë
    -0.73
    adra
    -0.71
    nee
    -0.70
    bley
    -0.70
    akening
    -0.69
     Flavoring
    -0.69
    oval
    -0.68
    POSITIVE LOGITS
    payers
    1.12
     rate
    1.08
    Rate
    1.01
     rates
    0.97
     Rate
    0.95
    payer
    0.94
     ratios
    0.82
    hyde
    0.80
     fluctuations
    0.78
     ratio
    0.78
    Activations Density 0.020%

    No Known Activations