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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 2486
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by the verb "say" or "regard"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ancial
    -0.59
     Screw
    -0.57
    ammy
    -0.57
     surprises
    -0.56
     refresh
    -0.56
     concentration
    -0.56
    hang
    -0.55
     Supply
    -0.55
     YES
    -0.55
     compatibility
    -0.54
    POSITIVE LOGITS
     termed
    1.49
     dubbed
    1.16
     euphem
    1.10
     deems
    1.10
    called
    1.09
     dub
    1.09
     called
    1.08
     deem
    1.06
     deemed
    1.03
     perceive
    1.00
    Activations Density 0.121%

    No Known Activations