© 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. 3-RES-JB
    11. 6007
    Prev
    Next
    INDEX
    Explanations

    names, especially Japanese names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those with the name "Kaz."

    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
    ACTED
    -0.80
    éļ
    -0.70
    aneous
    -0.70
    ersion
    -0.70
    gotten
    -0.65
    iscopal
    -0.65
     Failure
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.65
    itia
    -0.65
    20439
    -0.62
    POSITIVE LOGITS
     Kaz
    0.98
    amaz
    0.90
    hou
    0.85
    imoto
    0.82
    ivan
    0.82
    uki
    0.82
    onis
    0.80
    laus
    0.80
    terness
    0.80
    akov
    0.79
    Activations Density 0.006%

    No Known Activations