© 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. 7-RES-JB
    11. 24014
    Prev
    Next
    INDEX
    Explanations

    descriptive terms relating to situations of urgency or crisis

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "desperate" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roma
    -0.88
    arthed
    -0.81
    insula
    -0.80
    rats
    -0.76
    cript
    -0.74
    gemony
    -0.72
    lav
    -0.72
    ences
    -0.71
    Ģ
    -0.69
    afort
    -0.69
    POSITIVE LOGITS
     pleas
    0.85
     desperately
    0.82
     plea
    0.76
     desperate
    0.75
     necessity
    0.75
     begging
    0.73
     Measures
    0.73
     pleading
    0.73
     bargain
    0.72
     clinging
    0.72
    Activations Density 0.038%

    No Known Activations