© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 10215
    Prev
    Next
    INDEX
    Explanations

    the word "get" with varying degrees of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    variations of the verb "get."

    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
     marked
    -0.67
     marks
    -0.65
     mark
    -0.61
     pains
    -0.60
     chambers
    -0.58
     aud
    -0.57
     lines
    -0.57
     walls
    -0.56
     scaling
    -0.55
     surrounding
    -0.55
    POSITIVE LOGITS
    get
    4.10
    gets
    2.54
    getting
    2.27
    GET
    2.20
    got
    1.73
    Get
    1.71
    gotten
    1.68
    getic
    1.52
    give
    1.48
    gettable
    1.35
    Activations Density 0.007%

    No Known Activations