© 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. 10-RES-JB
    11. 18704
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing a positive or negative aspect of a situation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uum
    -0.88
    othal
    -0.85
     largeDownload
    -0.75
    apter
    -0.72
    trak
    -0.67
    odan
    -0.64
    bol
    -0.64
    URI
    -0.63
    REF
    -0.62
    akedown
    -0.60
    POSITIVE LOGITS
     happen
    1.09
     happening
    1.06
     happened
    1.05
     EVER
    0.94
     ever
    0.93
     Happ
    0.92
     imaginable
    0.88
     happens
    0.88
     happ
    0.85
     Done
    0.80
    Activations Density 0.087%

    No Known Activations