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. 20497
    Prev
    Next
    INDEX
    Explanations

    words related to parts or components

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating parts of a series

    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
    enance
    -0.84
    antry
    -0.75
    agents
    -0.70
    intendent
    -0.70
    wered
    -0.69
    arians
    -0.69
     reacts
    -0.69
    ador
    -0.66
     Colo
    -0.64
    lambda
    -0.64
    POSITIVE LOGITS
     broader
    1.28
     larger
    1.22
     wider
    1.21
     continuum
    1.18
     concerted
    0.99
     trilogy
    0.98
     series
    0.97
     trend
    0.97
     constellation
    0.96
     longstanding
    0.93
    Activations Density 0.146%

    No Known Activations