© 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. 9-RES-JB
    11. 11504
    Prev
    Next
    INDEX
    Explanations

    personal or company names with a specific structure, possibly related to legal or financial documents

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of numerical values or statistics within a text

    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
    boro
    -0.75
     homebrew
    -0.74
     Baxter
    -0.68
     Canter
    -0.66
     Hancock
    -0.66
     Ginny
    -0.66
     Davis
    -0.64
     temptation
    -0.63
     Berry
    -0.63
     Blake
    -0.63
    POSITIVE LOGITS
    Moreover
    1.04
    Therefore
    1.02
    à¨
    1.00
    à¦
    0.94
    Pakistan
    0.94
    ³³³³³³³³³³³³³³³³
    0.94
    à©
    0.94
    Express
    0.92
    However
    0.90
    Furthermore
    0.89
    Activations Density 0.400%

    No Known Activations