© 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. 11-RES-JB
    11. 7169
    Prev
    Next
    INDEX
    Explanations

    Direct speech attributions with 'said' followed by a specific person's name

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    berus
    -0.65
    pend
    -0.64
    \)
    -0.60
    phia
    -0.60
    gencies
    -0.58
    /
    -0.58
    DragonMagazine
    -0.58
    mentation
    -0.58
    Fit
    -0.57
    Availability
    -0.56
    POSITIVE LOGITS
     sarcast
    1.20
     rhet
    1.02
     onstage
    1.00
     bluntly
    0.99
     during
    0.94
     emphatically
    0.90
     angrily
    0.87
     forcefully
    0.86
     afterward
    0.85
     aloud
    0.82
    Activations Density 0.109%

    No Known Activations