© 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. 4-RES-JB
    11. 3357
    Prev
    Next
    INDEX
    Explanations

    references to the fictional character or brand "MegaMan"

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Mega Man" franchise, including its characters and titles

    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
    ANCE
    -0.87
    ance
    -0.82
    sburgh
    -0.78
     Lauder
    -0.76
    swer
    -0.76
    ding
    -0.76
    IENCE
    -0.71
    witz
    -0.67
    zbollah
    -0.66
    enance
    -0.64
    POSITIVE LOGITS
    xon
    0.94
    Upload
    0.93
    mega
    0.84
    her
    0.77
    economic
    0.76
    ventus
    0.76
    Mega
    0.74
    plex
    0.73
    charge
    0.73
    charging
    0.72
    Activations Density 0.014%

    No Known Activations