© 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. 2110
    Prev
    Next
    INDEX
    Explanations

    command lines or functions related to printing, such as printf or console.log

    oai_token-act-pair · gpt-3.5-turbo

    programming-related output statements and functions

    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
    laus
    -1.00
    plates
    -0.80
    ktop
    -0.79
    undai
    -0.75
    arsity
    -0.75
    agonists
    -0.69
    andals
    -0.68
    folio
    -0.68
    spring
    -0.66
    ulpt
    -0.66
    POSITIVE LOGITS
     gib
    0.81
     "$
    0.77
     "%
    0.76
    >>>>>>>>
    0.73
    Debug
    0.71
     "[
    0.69
    Error
    0.69
     println
    0.68
     cout
    0.68
    Continue
    0.65
    Activations Density 0.034%

    No Known Activations