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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20703
    Prev
    Next
    INDEX
    Explanations

    words expressing agreement or admiration

    oai_token-act-pair · gpt-3.5-turbo

    expressions of admiration and agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ixir
    -0.57
     us
    -0.57
    zbollah
    -0.56
     me
    -0.56
     Us
    -0.50
     computing
    -0.50
    nia
    -0.50
     suspended
    -0.48
     seaw
    -0.48
    %]
    -0.48
    POSITIVE LOGITS
     theirs
    1.17
     them
    1.06
     hers
    1.05
     him
    0.97
    them
    0.97
     THEIR
    0.95
    their
    0.93
    his
    0.93
     THEM
    0.93
     their
    0.89
    Activations Density 0.508%

    No Known Activations