© 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
    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. 9248
    Prev
    Next
    INDEX
    Explanations

    mentions of large financial amounts, typically in the context of millionaires and billionaires

    oai_token-act-pair · gpt-3.5-turbo

    references to high-value financial terms, particularly related to billions and millions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    uberty
    -0.65
     Metatron
    -0.65
    GY
    -0.64
    CHR
    -0.63
     Ober
    -0.61
     Gillespie
    -0.59
     stern
    -0.58
    ICES
    -0.58
    ©¶æ
    -0.57
     exha
    -0.57
    POSITIVE LOGITS
    aires
    1.79
    aire
    1.73
    dollar
    1.49
     dollar
    1.42
     Dollar
    1.21
    naire
    1.17
     dollars
    1.15
     Dollars
    0.97
    ths
    0.95
     bucks
    0.91
    Activations Density 0.053%

    No Known Activations