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

    Neuronpedia

    Jacobian LensNEW
    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. 15875
    Prev
    Next
    INDEX
    Explanations

    the word "not" preceding another verb

    oai_token-act-pair · gpt-3.5-turbo

    negative assertions or denials

    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
     Pric
    -0.71
    lined
    -0.68
     Cutter
    -0.66
     Tow
    -0.65
     Eisen
    -0.64
     Gone
    -0.63
     yeah
    -0.63
     Canaveral
    -0.63
    GGGGGGGG
    -0.62
    itiz
    -0.62
    POSITIVE LOGITS
     intend
    1.18
     hesitate
    1.12
     belong
    1.08
     reside
    1.07
     exist
    1.05
     condone
    1.04
     specify
    1.03
     necessarily
    1.03
     discriminate
    1.02
     approve
    1.00
    Activations Density 0.100%

    No Known Activations