© 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. 12070
    Prev
    Next
    INDEX
    Explanations

    past-tense verb phrases related to specific technical actions or changes

    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
     ÂŃ
    -0.90
     Rodham
    -0.83
     Pulitzer
    -0.82
     Teresa
    -0.79
     Dorothy
    -0.79
     Hers
    -0.75
     Wichita
    -0.74
     Faul
    -0.74
     Bethlehem
    -0.74
    CTV
    -0.73
    POSITIVE LOGITS
     devs
    1.44
     workaround
    1.40
     optimizations
    1.29
     implementations
    1.22
     implemented
    1.22
     optimization
    1.20
    fixes
    1.19
     tweaks
    1.18
     deprecated
    1.16
     tweak
    1.15
    Activations Density 0.653%

    No Known Activations