© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 8502
    Prev
    Next
    INDEX
    Explanations

    terms related to financial investments and portfolios

    oai_token-act-pair · gpt-3.5-turbo

    references to financial portfolios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nai
    -0.79
    thia
    -0.71
    heart
    -0.69
    tale
    -0.68
    phe
    -0.68
    phrine
    -0.65
    hearted
    -0.65
    hig
    -0.62
    lon
    -0.62
    nin
    -0.62
    POSITIVE LOGITS
     portfolios
    1.14
    folio
    1.12
    folios
    1.07
     portfolio
    1.07
     holdings
    1.03
     mates
    0.80
    olicy
    0.80
    builder
    0.76
    imately
    0.76
     allocations
    0.74
    Activations Density 0.026%

    No Known Activations