© 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. 11-RES-JB
    11. 22341
    Prev
    Next
    INDEX
    Explanations

    references to financial and economic data

    oai_token-act-pair · gpt-3.5-turbo

    references to income and financial statistics

    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
     maths
    -0.95
     Nasa
    -0.89
     Nato
    -0.87
     civilisation
    -0.83
     stuff
    -0.82
     flavours
    -0.81
     rubbish
    -0.81
     favourites
    -0.80
     Notting
    -0.80
     Anyway
    -0.79
    POSITIVE LOGITS
     adversely
    1.05
     materially
    0.93
     âĪ¼
    0.92
     utilize
    0.90
     respondent
    0.90
     Plaint
    0.89
     utilized
    0.89
     utilizing
    0.88
     approximately
    0.88
     petitioner
    0.86
    Activations Density 1.239%

    No Known Activations