© 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. 2115
    Prev
    Next
    INDEX
    Explanations

    mentions related to a specific publication or brand

    oai_token-act-pair · gpt-3.5-turbo

    references to the content and context of the magazine "Famitsu."

    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
    cot
    -0.74
    icative
    -0.72
    cart
    -0.72
    edly
    -0.70
    sea
    -0.68
     Presence
    -0.66
     Gutenberg
    -0.64
    etheless
    -0.63
    ruck
    -0.62
     Archdemon
    -0.62
    POSITIVE LOGITS
    itsu
    1.13
    hiro
    1.01
    arate
    0.87
    arist
    0.83
    yu
    0.81
    unin
    0.80
    utsu
    0.79
    imoto
    0.78
    uchi
    0.76
    ya
    0.75
    Activations Density 0.013%

    No Known Activations