© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 17867
    Prev
    Next
    INDEX
    Explanations

    phrases that contradict a preceding statement or expectation

    oai_token-act-pair · gpt-3.5-turbo

    negations and phrases indicating what something is not

    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
    ãģ®ç
    -0.73
    ngth
    -0.69
    çīĪ
    -0.67
    ividual
    -0.67
    icks
    -0.64
    éĥ
    -0.62
     showc
    -0.62
     Links
    -0.61
    wives
    -0.60
    agos
    -0.60
    POSITIVE LOGITS
     necessarily
    1.08
     happening
    0.91
    rael
    0.82
     exactly
    0.80
    icable
    0.78
     uncommon
    0.78
    actly
    0.77
     coincidence
    0.76
     happ
    0.74
     detract
    0.73
    Activations Density 0.107%

    No Known Activations