© 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. 11-RES-JB
    11. 10207
    Prev
    Next
    INDEX
    Explanations

    financial information and numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to financial records and high values in economic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     horm
    -0.80
     hazard
    -0.72
    inelli
    -0.65
    olicy
    -0.65
     inexper
    -0.64
    optional
    -0.63
     withhold
    -0.62
    azard
    -0.62
     withholding
    -0.62
    aghetti
    -0.62
    POSITIVE LOGITS
     surpassed
    1.07
     surpass
    1.03
     USD
    0.96
     valuation
    0.92
     eclips
    0.92
     Ethereum
    0.85
     Alexa
    0.85
     Coinbase
    0.83
     BTC
    0.82
     climbed
    0.82
    Activations Density 0.260%

    No Known Activations