© 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. 4-RES-JB
    11. 1307
    Prev
    Next
    INDEX
    Explanations

    JavaScript code-related terms or functions, particularly those related to "get" operations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "get" in various programming contexts

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

    No Comments

    Negative Logits
    isine
    -0.73
    enture
    -0.70
    SPONSORED
    -0.70
    aughs
    -0.69
     restraint
    -0.67
    ingen
    -0.66
    olini
    -0.65
    agna
    -0.65
     prophes
    -0.65
    rimination
    -0.64
    POSITIVE LOGITS
     rid
    0.93
    TING
    0.90
    appings
    0.74
    maps
    0.73
     Started
    0.73
    ter
    0.72
    xit
    0.71
    emp
    0.71
    olate
    0.70
    ters
    0.69
    Activations Density 0.041%

    No Known Activations