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. 1-RES-JB
    6. 11786
    Prev
    Next
    INDEX
    Explanations

    academic institutions and departments related to science

    oai_token-act-pair · gpt-3.5-turbo

    references to various academic disciplines related to sciences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adding
    -0.73
    template
    -0.66
    own
    -0.62
    acting
    -0.62
    leg
    -0.62
    usher
    -0.61
     deserted
    -0.60
    aggressive
    -0.60
    shr
    -0.60
    irth
    -0.60
    POSITIVE LOGITS
     Sciences
    1.32
     sciences
    1.05
    terday
    0.86
     Profession
    0.85
    istries
    0.82
     Neuroscience
    0.82
     Pwr
    0.80
     Laboratories
    0.79
    pecially
    0.78
    udo
    0.76
    Activations Density 0.005%

    No Known Activations