© 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. 10-RES-JB
    11. 12750
    Prev
    Next
    INDEX
    Explanations

    financial figures and related keywords related to money transactions

    oai_token-act-pair · gpt-3.5-turbo

    references to financial transactions or funding

    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
    iquette
    -0.90
    ophobia
    -0.82
    é»Ĵ
    -0.79
    Ħ¢
    -0.77
    ophobic
    -0.73
    zona
    -0.72
    ierre
    -0.72
    opath
    -0.69
    odox
    -0.69
    acons
    -0.68
    POSITIVE LOGITS
     $
    1.59
     taxpayers
    1.39
    $
    1.38
     reimburse
    1.30
     repayment
    1.29
     reimb
    1.28
     totaling
    1.28
     repaid
    1.28
     ($
    1.27
     repay
    1.27
    Activations Density 0.511%

    No Known Activations