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

    Neuronpedia

    APICircuit 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. 3-RES-JB
    6. 2292
    Prev
    Next
    INDEX
    Explanations

    financial information and company-related terms

    oai_token-act-pair · gpt-3.5-turbo

    financial metrics and corporate performance indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ä
    -0.76
    accompanied
    -0.76
     unaccompanied
    -0.74
    ĸļ
    -0.74
     deport
    -0.74
     ultras
    -0.68
     grammar
    -0.65
     checkpoints
    -0.64
     Auschwitz
    -0.64
    anguage
    -0.64
    POSITIVE LOGITS
     investors
    1.36
     Investors
    1.35
     investor
    1.27
    daq
    1.24
     shareholders
    1.23
    NYSE
    1.23
     Securities
    1.23
     Investor
    1.22
    Shares
    1.19
     hedge
    1.18
    Activations Density 0.903%

    No Known Activations