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. 2-RES-JB
    6. 9689
    Prev
    Next
    INDEX
    Explanations

    the word "elsewhere" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to locations outside of the current context or discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Moon
    -0.67
    1000
    -0.62
     Scientist
    -0.62
    nex
    -0.61
    root
    -0.60
    ³³³³³³³³³³³³³³³³
    -0.59
    hop
    -0.58
    sha
    -0.58
    oly
    -0.57
    1993
    -0.57
    POSITIVE LOGITS
     behavi
    0.93
     describ
    0.91
    worldly
    0.88
    abouts
    0.84
    wcs
    0.82
     abroad
    0.81
    é¾įåĸļ士
    0.81
    vernment
    0.80
    isphere
    0.80
     nodd
    0.78
    Activations Density 0.003%

    No Known Activations