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. 0-RES-JB
    6. 22099
    Prev
    Next
    INDEX
    Explanations

    the word "mother" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of monotheism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Challenger
    -0.68
     2000
    -0.65
     Dem
    -0.65
     Labrador
    -0.63
     2012
    -0.62
     gangs
    -0.61
     2008
    -0.61
     modules
    -0.60
     2010
    -0.59
     trenches
    -0.59
    POSITIVE LOGITS
    othe
    5.12
    othes
    1.43
    ithe
    1.41
    othing
    1.37
    athe
    1.32
    ocry
    1.30
    ophy
    1.25
    othy
    1.24
    oth
    1.20
    ethe
    1.18
    Activations Density 0.032%

    No Known Activations