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. 4-RES-JB
    6. 21377
    Prev
    Next
    INDEX
    Explanations

    capitalized acronyms 'BR' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "BR" followed by numerical values or identifiers

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

    No Comments

    Negative Logits
    eers
    -0.82
    geist
    -0.76
    ãĥĥãĥĪ
    -0.74
    ãĥ¼ãĥĨãĤ£
    -0.73
     Gutenberg
    -0.72
     Homo
    -0.71
    ographed
    -0.70
    ãĥĩãĤ£
    -0.67
    bred
    -0.64
    ãĤ®
    -0.64
    POSITIVE LOGITS
    OAD
    1.16
    ushed
    0.98
    acket
    0.96
    ackets
    0.92
    anca
    0.92
    ICK
    0.92
    ACE
    0.92
    andon
    0.92
    OCK
    0.92
    RR
    0.92
    Activations Density 0.006%

    No Known Activations