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. 656
    Prev
    Next
    INDEX
    Explanations

    the word "there" as part of various expressions or statements

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "there" in various contexts

    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
     conf
    -0.65
     dec
    -0.65
     target
    -0.64
     origin
    -0.63
     privilege
    -0.63
     base
    -0.62
     heavily
    -0.62
     form
    -0.62
     mock
    -0.62
     bl
    -0.62
    POSITIVE LOGITS
    there
    3.44
    they
    1.74
     THERE
    1.66
    these
    1.49
    There
    1.46
    the
    1.41
    you
    1.39
     there
    1.38
    everyone
    1.37
    this
    1.36
    Activations Density 0.007%

    No Known Activations