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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 7512
    Prev
    Next
    INDEX
    Explanations

    information related to numerical averages such as median income, average salary, and life expectancy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to median and average statistics, particularly regarding income and financial metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¦ãĤ¹
    -0.90
    atography
    -0.88
    Ü
    -0.83
    onduct
    -0.80
    pecially
    -0.79
    ãĤ¤ãĥĪ
    -0.79
    acus
    -0.78
    apons
    -0.75
    afort
    -0.74
    ordes
    -0.71
    POSITIVE LOGITS
     lifespan
    1.13
     amount
    1.09
     hourly
    1.04
     annual
    1.02
     duration
    1.02
     person
    1.00
     weekday
    1.00
     age
    0.98
     number
    0.98
     length
    0.97
    Activations Density 0.047%

    No Known Activations