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. 21237
    Prev
    Next
    INDEX
    Explanations

    dates or time-related phrases followed by an action

    oai_token-act-pair · gpt-3.5-turbo

    text segments that begin with the word "Earlier" and indicate timing or sequence

    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
    adr
    -0.75
     favour
    -0.73
    rouse
    -0.70
    venge
    -0.63
    icket
    -0.61
     favor
    -0.61
    aternity
    -0.60
    #$
    -0.59
    natureconservancy
    -0.59
    iger
    -0.59
    POSITIVE LOGITS
    etheless
    0.98
    noon
    0.96
     Thoughts
    0.91
     Ago
    0.86
     editions
    0.81
     Reports
    0.79
     versions
    0.78
     Seasons
    0.77
     Releases
    0.77
     Stories
    0.76
    Activations Density 0.093%

    No Known Activations