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. 9-RES-JB
    6. 113
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names related to various topics, such as science, politics, and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific terminology or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.98
    atform
    -0.78
    tm
    -0.73
    è¦ļéĨĴ
    -0.71
    agna
    -0.70
    matically
    -0.63
     externalToEVAOnly
    -0.62
    rooms
    -0.61
    sheet
    -0.60
    Discussion
    -0.58
    POSITIVE LOGITS
    vironment
    1.15
    cia
    0.93
    venue
    0.93
    stadt
    0.91
    hao
    0.89
    ci
    0.88
    iewicz
    0.86
    ews
    0.85
    kowski
    0.83
    heimer
    0.82
    Activations Density 0.038%

    No Known Activations