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. 6-RES-JB
    6. 11309
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters or investigations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that relate to various topics or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LI
    -0.90
    ©¶æ¥µ
    -0.80
    herer
    -0.76
    icer
    -0.74
    Written
    -0.73
    SN
    -0.73
    Reviewed
    -0.70
    SUP
    -0.69
    ®
    -0.68
    lite
    -0.68
    POSITIVE LOGITS
     mater
    0.80
     whether
    0.72
     behalf
    0.71
     commerce
    0.70
     Export
    0.69
     UFOs
    0.68
     the
    0.66
     topics
    0.65
     those
    0.64
     sale
    0.64
    Activations Density 0.085%

    No Known Activations