© 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. 3-RES-JB
    11. 3734
    Prev
    Next
    INDEX
    Explanations

    file paths in Unix-like systems

    oai_token-act-pair · gpt-3.5-turbo

    file directory paths in a computer system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     warr
    -0.70
     Elliott
    -0.70
     Giov
    -0.69
     soaring
    -0.68
     Daly
    -0.67
     Moody
    -0.67
     creep
    -0.66
     apologised
    -0.66
     deceive
    -0.66
     Chambers
    -0.66
    POSITIVE LOGITS
    default
    1.15
    etc
    1.12
    modules
    1.06
    src
    1.05
    lib
    1.02
    input
    1.01
    index
    1.01
    library
    1.00
    shared
    0.99
    1000
    0.99
    Activations Density 0.061%

    No Known Activations