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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22691
    Prev
    Next
    INDEX
    Explanations

    terms related to meteorology

    oai_token-act-pair · gpt-3.5-turbo

    organizations and entities related to meteorology, human rights, and related political or environmental issues

    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
     silence
    -0.73
    idious
    -0.69
    theless
    -0.67
    rawdownloadcloneembedreportprint
    -0.64
    rely
    -0.64
     silenced
    -0.60
     apiece
    -0.60
     oneself
    -0.59
     toes
    -0.58
    arrow
    -0.57
    POSITIVE LOGITS
     Programme
    1.03
     Fund
    1.03
     Agency
    1.02
     Registry
    0.96
     Services
    0.96
     Consortium
    0.96
     Facility
    0.95
     Centre
    0.94
     Works
    0.93
     Organisation
    0.92
    Activations Density 0.484%

    No Known Activations