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. 3-RES-JB
    6. 1321
    Prev
    Next
    INDEX
    Explanations

    phrases related to points of interest or focus in a text

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "matter of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asks
    -0.82
     reperto
    -0.79
    ials
    -0.75
     Cosponsors
    -0.73
    ositories
    -0.72
    irs
    -0.71
    uctions
    -0.70
    aucuses
    -0.70
    ities
    -0.69
    riers
    -0.67
    POSITIVE LOGITS
     sorts
    1.06
     course
    0.98
    course
    0.85
    icial
    0.81
     theirs
    0.78
     ours
    0.71
    rontal
    0.66
    shoot
    0.65
    ordinary
    0.63
     hers
    0.62
    Activations Density 0.380%

    No Known Activations