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

    Neuronpedia

    APICircuit 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. 9-RES-JB
    6. 21831
    Prev
    Next
    INDEX
    Explanations

    numerical values or data written in a specific format (e.g., dates, measurements) in the text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pex
    -0.90
     psi
    -0.89
     Piper
    -0.79
     nano
    -0.78
     Pony
    -0.76
    cms
    -0.76
    TC
    -0.76
     Tablet
    -0.75
     Pom
    -0.75
     Cerberus
    -0.73
    POSITIVE LOGITS
     17
    1.39
    17
    1.32
     16
    1.12
    16
    1.10
     18
    1.08
    18
    1.05
     eighteenth
    1.02
     seventeen
    0.90
     1917
    0.87
     169
    0.85
    Activations Density 0.198%

    No Known Activations