© 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. 4-RES-JB
    11. 2419
    Prev
    Next
    INDEX
    Explanations

    functions and programming code related to text processing

    oai_token-act-pair · gpt-3.5-turbo

    programming-related terms and function calls in code

    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
    è¦ļéĨĴ
    -0.65
     refres
    -0.65
     ages
    -0.65
     scares
    -0.64
     volunt
    -0.63
    rament
    -0.61
    orage
    -0.61
     cuts
    -0.60
     vanishing
    -0.60
    asking
    -0.57
    POSITIVE LOGITS
    #$
    0.73
    ĸļ
    0.72
     Hague
    0.72
    ignore
    0.71
     Direction
    0.70
     Married
    0.70
     Sphere
    0.69
    ¿
    0.66
     Baird
    0.64
     Provision
    0.64
    Activations Density 0.404%

    No Known Activations