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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 22492
    Prev
    Next
    INDEX
    Explanations

    references related to a specific video game character named Sonic

    oai_token-act-pair · gpt-3.5-turbo

    references to "Sonic" or "sonic" in various contexts, particularly related to the gaming franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    een
    -1.04
    ded
    -0.98
    yer
    -0.81
    sburgh
    -0.80
    ding
    -0.80
    rey
    -0.76
    enance
    -0.76
    fully
    -0.73
    enegger
    -0.70
    л
    -0.70
    POSITIVE LOGITS
    otin
    0.90
    olor
    0.79
     Screw
    0.78
     Boom
    0.78
    ãĥ³ãĤ¸
    0.77
     Youth
    0.72
     Generations
    0.71
    ucle
    0.70
    omic
    0.70
    osis
    0.69
    Activations Density 0.067%

    No Known Activations