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

    Neuronpedia

    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. 2986
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negation or contradiction

    oai_token-act-pair · gpt-3.5-turbo
    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
    ngth
    -0.77
     showc
    -0.75
     stalls
    -0.73
    ãģ®ç
    -0.73
    banks
    -0.73
    icks
    -0.70
    tests
    -0.67
    WAY
    -0.65
     arsen
    -0.65
    éĥ
    -0.64
    POSITIVE LOGITS
     necessarily
    1.38
     exactly
    0.97
    icable
    0.88
     entirely
    0.87
     uncommon
    0.87
    withstanding
    0.86
    rael
    0.83
     happening
    0.82
    actly
    0.82
    eworthy
    0.81
    Activations Density 0.146%

    No Known Activations