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. 8-RES-JB
    6. 21464
    Prev
    Next
    INDEX
    Explanations

    the phrase "rolling out" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "rolling out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uo
    -0.67
    yll
    -0.66
    masters
    -0.66
    deen
    -0.65
    shaw
    -0.63
    arine
    -0.62
    hai
    -0.62
    inks
    -0.62
    woman
    -0.60
    ently
    -0.60
    POSITIVE LOGITS
     invitations
    0.77
    wards
    0.76
     Archdemon
    0.75
    eatures
    0.74
    ihilation
    0.72
     sleeves
    0.70
     CCTV
    0.69
     curtains
    0.65
    undown
    0.65
     sidewalks
    0.64
    Activations Density 0.056%

    No Known Activations