© 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. 8498
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparison or similarity

    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
     shalt
    -0.79
    interrupted
    -0.77
    aunder
    -0.73
    quished
    -0.71
    illed
    -0.67
    istant
    -0.64
     sacked
    -0.64
    istani
    -0.62
     Collider
    -0.62
    lost
    -0.61
    POSITIVE LOGITS
     nature
    1.26
     origin
    1.10
     appearance
    1.09
     stature
    1.08
     disguise
    1.06
     outlook
    1.05
     principle
    1.05
     comparison
    1.03
     terms
    1.03
     tone
    1.02
    Activations Density 0.157%

    No Known Activations