© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-JB
    11. 689
    Prev
    Next
    INDEX
    Explanations

    keywords related to the character "Sonic" from the Sonic the Hedgehog franchise

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the video game franchise "Sonic."

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

    No Comments

    Negative Logits
    een
    -0.85
    teen
    -0.84
    sburgh
    -0.76
    nob
    -0.73
    iers
    -0.72
    ardless
    -0.71
    rie
    -0.70
    mber
    -0.69
    urdue
    -0.69
    iences
    -0.68
    POSITIVE LOGITS
     Sonic
    1.00
     Boom
    0.91
    obl
    0.75
     Symphony
    0.73
     Unleashed
    0.72
     Eclipse
    0.71
     Doodle
    0.70
     Screw
    0.68
     Rhythm
    0.68
     oscill
    0.68
    Activations Density 0.012%

    No Known Activations