© 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. 2307
    Prev
    Next
    INDEX
    Explanations

    references to financial transactions or legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    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
    ibaba
    -0.84
    ictionary
    -0.84
     âĢº
    -0.81
    wich
    -0.72
    Minecraft
    -0.70
    Brexit
    -0.70
    gor
    -0.69
    Netflix
    -0.69
    pread
    -0.69
    ulhu
    -0.68
    POSITIVE LOGITS
     latter
    1.38
     remainder
    1.30
     ensuing
    1.20
     entire
    1.16
     offending
    1.09
     aforementioned
    1.06
     same
    1.05
     resultant
    1.04
     rest
    1.02
     entirety
    1.02
    Activations Density 0.834%

    No Known Activations