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. 11-RES-JB
    6. 4654
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting praise or recognition of deserving individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    ullivan
    -0.92
     convol
    -0.63
    cross
    -0.61
    ãĤ¨ãĥ«
    -0.60
    edd
    -0.60
    inki
    -0.59
     Pastebin
    -0.59
    anches
    -0.58
    INS
    -0.58
    orph
    -0.57
    POSITIVE LOGITS
     praise
    1.16
     credit
    1.09
     recognition
    1.08
     admiration
    1.04
     applause
    1.04
     consideration
    0.98
     accol
    0.98
     gratitude
    0.97
     congratulations
    0.96
     respect
    0.96
    Activations Density 0.055%

    No Known Activations