© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 1975
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting advice or recommendations

    oai_token-act-pair · gpt-3.5-turbo

    sentences expressing the word "should" related to obligations or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ickets
    -0.66
    esters
    -0.57
    umble
    -0.57
    undred
    -0.54
    oxy
    -0.53
    undreds
    -0.52
    umbling
    -0.50
    ruck
    -0.50
    _>
    -0.50
    aye
    -0.49
    POSITIVE LOGITS
     should
    3.13
     shouldn
    2.70
    should
    2.60
     ought
    2.55
     SHOULD
    2.54
    Should
    1.98
     Should
    1.96
     deserves
    1.82
     MUST
    1.74
     must
    1.65
    Activations Density 0.057%

    No Known Activations