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. 11-RES-JB
    6. 19635
    Prev
    Next
    INDEX
    Explanations

    information related to weekly events, updates, contests, and schedules

    oai_token-act-pair · gpt-3.5-turbo

    information related to events and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    ���
    -0.91
    ��
    -0.83
    ����
    -0.77
     Hussein
    -0.76
    Ùĩ
    -0.76
     âĢķ
    -0.74
    س
    -0.73
     ÂŃ
    -0.73
    alkyrie
    -0.73
    ÂŃ
    -0.71
    POSITIVE LOGITS
     quarterly
    1.37
     newsletter
    1.37
     weekly
    1.35
     newsletters
    1.26
     monthly
    1.25
     deadlines
    1.24
     announcements
    1.23
     Newsletter
    1.22
     Monthly
    1.19
    weekly
    1.17
    Activations Density 0.588%

    No Known Activations