Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12-RES-JB
    6. 6980
    Prev
    Next
    INDEX
    Explanations

    information related to academic research and professional endeavors

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to significant contributions and collaborations in the arts and sciences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DERR
    -0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.66
    essim
    -0.64
    etheless
    -0.63
    nesday
    -0.63
    asy
    -0.61
    PsyNetMessage
    -0.60
    atson
    -0.60
    ridor
    -0.59
    Connector
    -0.59
    POSITIVE LOGITS
     magazines
    1.16
     museums
    1.16
     publications
    1.11
     colleges
    1.09
     universities
    1.08
     venues
    1.03
     charities
    1.01
     continents
    1.00
     nonprofits
    1.00
     festivals
    1.00
    Activations Density 0.412%

    No Known Activations