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. 10-RES-JB
    6. 2502
    Prev
    Next
    INDEX
    Explanations

    phrases related to high amounts of money or finance

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sic
    -0.39
    anwhile
    -0.37
    enegger
    -0.36
    _.
    -0.35
     helicop
    -0.31
    *.
    -0.31
     accordingly
    -0.31
    $$$$
    -0.30
     disadvant
    -0.30
    FFFF
    -0.29
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    0.35
    recated
    0.34
     isEnabled
    0.33
    Merit
    0.33
     ):
    0.32
     âĢº
    0.30
    isode
    0.30
    cookie
    0.30
    apixel
    0.29
    debian
    0.29
    Activations Density 2.391%

    No Known Activations