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. 4-RES-JB
    6. 5932
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizations or groups named "Friends."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Friends"

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

    No Comments

    Negative Logits
     concussion
    -0.60
    umbers
    -0.60
    gars
    -0.59
    rum
    -0.59
    itol
    -0.58
    OUT
    -0.58
    ribe
    -0.58
     utilitarian
    -0.57
    peat
    -0.57
    guns
    -0.57
    POSITIVE LOGITS
    hips
    1.12
     Friends
    1.12
    Friends
    0.84
    adelphia
    0.84
    liness
    0.82
     Friend
    0.82
    hip
    0.81
    ystem
    0.80
    busters
    0.80
    ilial
    0.79
    Activations Density 0.018%

    No Known Activations