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. 10-RES-JB
    6. 15680
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and money management

    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
    ²¾
    -0.80
    dayName
    -0.78
    speak
    -0.69
    oland
    -0.67
    iasco
    -0.66
    haus
    -0.64
     Surgery
    -0.64
     Methodist
    -0.64
    ogun
    -0.64
    emale
    -0.63
    POSITIVE LOGITS
     profits
    1.41
     billions
    1.38
     money
    1.33
     funds
    1.24
     millions
    1.21
     revenues
    1.19
     royalties
    1.18
     profit
    1.17
     cash
    1.17
     revenue
    1.17
    Activations Density 0.355%

    No Known Activations