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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 20892
    Prev
    Next
    INDEX
    Explanations

    personal statements where someone is told something or has to do something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of obligation or decisions involving individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.83
    omatic
    -0.68
    uel
    -0.66
     Camb
    -0.64
     Wad
    -0.63
     attm
    -0.63
     Various
    -0.62
    Chel
    -0.62
     Dart
    -0.61
    ical
    -0.60
    POSITIVE LOGITS
     shouldn
    1.20
     should
    1.10
     SHOULD
    0.98
     ought
    0.96
    should
    0.96
     MUST
    0.95
    must
    0.91
    'll
    0.90
     must
    0.90
     owed
    0.90
    Activations Density 0.182%

    No Known Activations