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. 17547
    Prev
    Next
    INDEX
    Explanations

    mentions of the company IBM

    oai_token-act-pair · gpt-3.5-turbo

    mentions of IBM

    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
    uberty
    -0.74
     Furious
    -0.70
    nels
    -0.68
    fully
    -0.67
    adows
    -0.67
    adow
    -0.67
    owder
    -0.66
    ibus
    -0.66
    liam
    -0.66
    Spoiler
    -0.66
    POSITIVE LOGITS
     Watson
    1.05
     IBM
    0.93
    ython
    0.76
    intosh
    0.73
     typew
    0.73
    kernel
    0.72
     Advantage
    0.72
     Doodle
    0.71
     Keyboard
    0.70
     cane
    0.70
    Activations Density 0.010%

    No Known Activations