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. 7-RES-JB
    6. 6652
    Prev
    Next
    INDEX
    Explanations

    instances where the term "beginning" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    the concept of beginnings or starting points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itsch
    -0.79
    ategor
    -0.77
    aths
    -0.73
    osponsors
    -0.67
    rero
    -0.67
    ilty
    -0.66
    ouri
    -0.65
    otton
    -0.65
    etsy
    -0.64
    adish
    -0.64
    POSITIVE LOGITS
     anew
    1.00
    nings
    0.92
     stages
    0.87
     thereof
    0.82
    EGIN
    0.71
     phases
    0.71
    theless
    0.69
    ãĤ½
    0.69
     kickoff
    0.65
    backer
    0.65
    Activations Density 0.029%

    No Known Activations