© 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. 3-RES-JB
    11. 18257
    Prev
    Next
    INDEX
    Explanations

    cities and locations

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and place names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VALUE
    -0.78
    Mach
    -0.74
    lyak
    -0.70
    ãĤ¯
    -0.69
     Euros
    -0.69
    intern
    -0.67
    akable
    -0.65
    Euro
    -0.64
    aphael
    -0.61
    letter
    -0.61
    POSITIVE LOGITS
     County
    1.19
     Heights
    1.14
     Township
    1.08
     Junction
    1.05
    shire
    1.03
     Borough
    0.99
     Rapids
    0.99
     suburbs
    0.98
     Springs
    0.91
    burgh
    0.90
    Activations Density 0.263%

    No Known Activations