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. 14542
    Prev
    Next
    INDEX
    Explanations

    words related to physical actions or objects that can be pushed

    oai_token-act-pair · gpt-3.5-turbo

    common suffixes or phonetic patterns in words

    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
     Cummings
    -0.66
    OND
    -0.62
     Grimes
    -0.61
    Introduced
    -0.61
    ALLY
    -0.61
    ATTLE
    -0.61
     dispatch
    -0.55
     Frequ
    -0.54
     Duff
    -0.54
    schild
    -0.53
    POSITIVE LOGITS
    ongyang
    1.03
    sylvania
    0.96
    merga
    0.88
    haps
    0.87
    umatic
    0.84
    Cola
    0.83
    adium
    0.81
    chedel
    0.79
    asant
    0.79
    sburgh
    0.78
    Activations Density 0.085%

    No Known Activations