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. 20726
    Prev
    Next
    INDEX
    Explanations

    complex phrases of personal opinions or statements

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinion or individual beliefs

    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
    '.
    -0.91
    `.
    -0.88
    ''.
    -0.87
    ".
    -0.86
    .''.
    -0.83
    .......
    -0.77
    .''
    -0.75
    .</
    -0.75
    ".[
    -0.75
    .ãĢį
    -0.74
    POSITIVE LOGITS
     playbook
    0.73
     meanwhile
    0.59
     favorites
    0.58
     swath
    0.57
     Slate
    0.57
     gray
    0.56
     curs
    0.52
     quirks
    0.51
     backstory
    0.51
     gri
    0.50
    Activations Density 1.512%

    No Known Activations