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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12-RES-JB
    6. 6983
    Prev
    Next
    INDEX
    Explanations

    controversial or debatable statements within a text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    discussions surrounding dietary beliefs and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ô
    -1.02
    20439
    -1.01
    Þ
    -1.01
     Cosponsors
    -0.97
    ò
    -0.97
    ß
    -0.97
    ñ
    -0.96
    interstitial
    -0.95
    ô
    -0.91
    ERC
    -0.89
    POSITIVE LOGITS
     invented
    1.21
     scientifically
    1.11
     vanished
    1.05
     dispro
    1.04
     biologically
    1.03
     enslaved
    1.02
     millennia
    1.02
     extinct
    1.00
     invent
    1.00
     discredited
    1.00
    Activations Density 0.698%

    No Known Activations