© 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. 17099
    Prev
    Next
    INDEX
    Explanations

    information related to significant changes or trends in data

    oai_token-act-pair · gpt-3.5-turbo

    points related to economic trends and financial data

    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
     voic
    -0.90
    ĸļ
    -0.78
     blasp
    -0.77
     etiquette
    -0.77
     authent
    -0.77
    iquette
    -0.74
     lockdown
    -0.73
     decorated
    -0.73
     accus
    -0.71
     undercover
    -0.71
    POSITIVE LOGITS
     GDP
    1.23
    Average
    1.22
    flation
    1.21
     forecasts
    1.18
    Chart
    1.18
     Unemployment
    1.16
     Adjusted
    1.15
     fluctuations
    1.11
     Growth
    1.09
     Estimates
    1.09
    Activations Density 0.814%

    No Known Activations