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. 10-RES-JB
    6. 22624
    Prev
    Next
    INDEX
    Explanations

    words with possessive contractions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the contraction "em" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     polyg
    -0.78
     lapse
    -0.73
     collabor
    -0.69
     Indonesian
    -0.68
     comprehens
    -0.67
     equ
    -0.64
     sympathetic
    -0.64
     "<
    -0.63
     detail
    -0.63
     Swedish
    -0.62
    POSITIVE LOGITS
    til
    1.68
    cause
    1.61
    Cause
    1.49
    tis
    1.34
    Interstitial
    1.33
    Mech
    1.33
    Course
    1.22
    neath
    1.19
    Mania
    1.16
    round
    1.14
    Activations Density 0.039%

    No Known Activations