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. 20553
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Rapport"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of names related to reporting or journalism

    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
    ãĥĸ
    -0.71
    gling
    -0.71
    ãĥĪ
    -0.64
     Viking
    -0.64
    Reloaded
    -0.63
     bowel
    -0.62
     shelves
    -0.61
    ERAL
    -0.61
     amber
    -0.60
     symbolic
    -0.60
    POSITIVE LOGITS
     Rapp
    1.15
    eport
    0.97
    eur
    0.91
    ett
    0.90
    irtual
    0.89
    hett
    0.87
    etz
    0.84
    enter
    0.82
    ache
    0.80
    azz
    0.78
    Activations Density 0.010%

    No Known Activations