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. 21029
    Prev
    Next
    INDEX
    Explanations

    words ending in '-ically'

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that end with the suffix '-ically'

    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
     thence
    -0.60
     Titans
    -0.59
    dain
    -0.55
     yesterday
    -0.55
     Won
    -0.55
     Ald
    -0.54
     Sent
    -0.53
     htt
    -0.53
     light
    -0.53
     goodbye
    -0.52
    POSITIVE LOGITS
    ically
    4.38
    ical
    2.36
    icals
    2.21
    ICAL
    1.99
    atically
    1.96
    istically
    1.94
    ics
    1.93
    icians
    1.90
    urally
    1.77
    ologically
    1.76
    Activations Density 0.017%

    No Known Activations