Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 10240
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of people or places that start with "Th"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Thad" or similar variations

    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
     Reloaded
    -0.91
    ãģ®éŃĶ
    -0.91
    ITED
    -0.88
    76561
    -0.87
    assetsadobe
    -0.83
    keeping
    -0.76
    ãĤŃ
    -0.76
    ãģĭ
    -0.75
    915
    -0.74
    Spoiler
    -0.73
    POSITIVE LOGITS
    irteen
    1.08
    reshold
    1.05
    irst
    1.03
    umb
    1.03
    orne
    1.01
    ought
    1.01
    istle
    1.00
    umbnail
    0.98
    orns
    0.98
    orough
    0.97
    Activations Density 0.015%

    No Known Activations