© 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. 10-RES-JB
    11. 4406
    Prev
    Next
    INDEX
    Explanations

    names of individuals and captions from photos

    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
    mine
    -0.68
    âĢķ
    -0.67
     âĢķ
    -0.66
    âĵĺ
    -0.65
    kees
    -0.65
     pronouns
    -0.64
     whatsoever
    -0.64
    pled
    -0.62
    Characters
    -0.61
    something
    -0.61
    POSITIVE LOGITS
     Associated
    1.09
     Chronicle
    1.08
     NYT
    1.04
     Tribune
    1.00
     Reporter
    0.98
     Globe
    0.92
     NPR
    0.85
     AFP
    0.85
     Staff
    0.84
     Contribut
    0.84
    Activations Density 0.050%

    No Known Activations