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. 10-RES-JB
    6. 17771
    Prev
    Next
    INDEX
    Explanations

    phrases related to a consistent or ongoing presence or action

    oai_token-act-pair · gpt-3.5-turbo

    the recurring phrase "always."

    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
    channelAvailability
    -0.73
    ace
    -0.70
     clicks
    -0.66
    atch
    -0.65
     compilation
    -0.63
     Spray
    -0.63
     Warden
    -0.63
    Generic
    -0.62
    heimer
    -0.60
    ACTION
    -0.60
    POSITIVE LOGITS
     been
    1.40
    been
    1.28
     existed
    1.13
     resided
    1.11
     struggled
    1.07
     relied
    1.05
     maintained
    1.05
     belonged
    1.05
     depended
    1.00
     Been
    0.98
    Activations Density 0.067%

    No Known Activations