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. 14296
    Prev
    Next
    INDEX
    Explanations

    words related to establishing a connection or link

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "connecting" and its various forms

    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
     Sack
    -0.78
    lie
    -0.77
    landers
    -0.69
    CAST
    -0.64
    Skin
    -0.63
    apo
    -0.63
     Rove
    -0.61
    sort
    -0.61
    Beer
    -0.61
     Noon
    -0.61
    POSITIVE LOGITS
     connecting
    1.77
    amental
    1.37
    enting
    1.22
    cens
    1.16
    kaya
    1.08
    eka
    1.06
     expressing
    1.01
    fortable
    0.95
    eva
    0.87
     voicing
    0.85
    Activations Density 0.046%

    No Known Activations