© 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. 2333
    Prev
    Next
    INDEX
    Explanations

    locations described by names and addresses

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "of" and its associated phrases

    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
    TPP
    -0.88
    Created
    -0.76
    Animation
    -0.75
    ipedia
    -0.72
    DragonMagazine
    -0.71
     vetted
    -0.68
    oS
    -0.68
    Refer
    -0.67
    Versions
    -0.66
     exerted
    -0.66
    POSITIVE LOGITS
     Queens
    1.21
     Arlington
    1.18
     Plymouth
    1.18
     Bronx
    1.18
     suburban
    1.17
     Pleasant
    1.17
     Wilmington
    1.17
     Rochester
    1.17
     Bedford
    1.15
     Newtown
    1.13
    Activations Density 0.183%

    No Known Activations