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

    Neuronpedia

    Jacobian LensNEW
    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. 20986
    Prev
    Next
    INDEX
    Explanations

    Japanese names that sound like they could be from a Miyazaki film

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to names and places

    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
    */(
    -0.85
    ħĭ
    -0.84
    IBLE
    -0.84
    ————
    -0.82
    umbn
    -0.76
    çīĪ
    -0.74
    ãĥ¼ãĥĨ
    -0.74
    ãĥ¼ãĥĨãĤ£
    -0.72
    FORMATION
    -0.70
    CRIP
    -0.70
    POSITIVE LOGITS
     Miy
    1.09
    azaki
    1.04
    ako
    1.00
    atures
    0.94
    abel
    0.93
    amoto
    0.92
    ota
    0.89
    adic
    0.89
    angu
    0.87
    ango
    0.87
    Activations Density 0.012%

    No Known Activations