© 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. 10-RES-JB
    11. 2899
    Prev
    Next
    INDEX
    Explanations

    descriptions related to financial and legal matters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial or economic conditions

    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
    entimes
    -0.80
     utilizing
    -0.72
    eger
    -0.69
     amongst
    -0.64
     utilize
    -0.63
    icip
    -0.61
    Recently
    -0.60
     acquaint
    -0.60
     particularly
    -0.59
     firsthand
    -0.58
    POSITIVE LOGITS
     Nope
    0.61
    xit
    0.60
    livion
    0.57
     +++
    0.56
     minus
    0.55
     Nobody
    0.54
     Mulcair
    0.53
     McConnell
    0.53
     nowhere
    0.53
     Fior
    0.52
    Activations Density 1.191%

    No Known Activations