© 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 EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 15397
    Prev
    Next
    INDEX
    Explanations

    specific text formats such as URLs or file paths with a colon followed by a backslash

    oai_token-act-pair · gpt-3.5-turbo

    symbols and technical terms related to web addresses and scripting

    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
    ik
    -0.68
     Festival
    -0.62
    azar
    -0.61
     marg
    -0.61
     Pyramid
    -0.60
    iq
    -0.60
     Breat
    -0.60
     Building
    -0.59
    phil
    -0.59
     Labyrinth
    -0.58
    POSITIVE LOGITS
    :"
    2.77
    :\
    2.73
    :'
    1.48
    ffer
    1.48
    :{
    1.24
    :,
    1.24
    :-
    1.17
    :/
    1.16
    :]
    1.09
    :[
    1.07
    Activations Density 0.032%

    No Known Activations