© 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. 0-RES-JB
    11. 13207
    Prev
    Next
    INDEX
    Explanations

    words that are used to show similarity in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "alike" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stro
    -0.51
    chin
    -0.51
     schedule
    -0.50
    arching
    -0.50
     scheduled
    -0.50
    oret
    -0.49
    usp
    -0.49
     limit
    -0.49
     Bend
    -0.48
    sche
    -0.48
    POSITIVE LOGITS
     alike
    4.90
     respectively
    1.96
     everywhere
    1.02
    together
    0.95
     thereof
    0.95
     extraord
    0.93
     interchangeable
    0.90
     versa
    0.90
     kindred
    0.88
    soever
    0.86
    Activations Density 0.013%

    No Known Activations