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. 13406
    Prev
    Next
    INDEX
    Explanations

    text written in a specific format: a colon followed by a statement or message

    oai_token-act-pair · gpt-3.5-turbo

    indicatives of written communication, such as quotes or citations

    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
     principals
    -0.70
     adversaries
    -0.70
     reconc
    -0.69
     territ
    -0.67
     stride
    -0.65
     undermin
    -0.64
     glac
    -0.62
     spills
    -0.61
     visitation
    -0.61
     comprom
    -0.61
    POSITIVE LOGITS
     âĨij
    1.25
    Originally
    1.08
    Show
    1.05
     Originally
    1.04
     Quote
    1.03
    Quote
    0.99
     Hmm
    0.98
    Hi
    0.97
    Hello
    0.95
     Hey
    0.95
    Activations Density 0.061%

    No Known Activations