© 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 EvalsExportsinterp-engineNEWAPI 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. 3375
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial crime and legal actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific symbol or character in the document

    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
    ividual
    -0.68
     protector
    -0.66
     marching
    -0.65
     shroud
    -0.65
     diving
    -0.64
     cycling
    -0.64
     staggered
    -0.64
     furthe
    -0.64
     rooting
    -0.63
     unconscious
    -0.62
    POSITIVE LOGITS
    £
    1.41
    ¬
    1.41
    º
    1.39
    Į
    1.39
    »
    1.38
    ¡
    1.37
    ª
    1.34
    į
    1.33
    ¹
    1.29
    ®
    1.29
    Activations Density 0.131%

    No Known Activations