© 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. 14696
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative consequences or obstacles

    oai_token-act-pair · gpt-3.5-turbo

    references to economic impacts and risks associated with consumers and industries

    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
    ³³³³
    -0.73
    eth
    -0.69
    ,[
    -0.66
    hest
    -0.65
    onomy
    -0.64
    edom
    -0.64
    ACTED
    -0.64
    kind
    -0.64
    wine
    -0.64
    ãģ®éŃĶ
    -0.63
    POSITIVE LOGITS
     unsuspecting
    1.19
     costly
    1.07
     otherwise
    1.05
     subsequent
    1.03
     pesky
    1.00
     unforeseen
    1.00
     newcomers
    1.00
     later
    0.95
     larger
    0.93
     other
    0.93
    Activations Density 0.791%

    No Known Activations