© 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. 4-RES-JB
    11. 23883
    Prev
    Next
    INDEX
    Explanations

    words related to routing and paths

    oai_token-act-pair · gpt-3.5-turbo

    terms related to routing and organization

    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
    endi
    -0.79
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.78
     Dunham
    -0.71
     Libre
    -0.67
     harb
    -0.67
    ATURE
    -0.67
    minster
    -0.61
    Leaks
    -0.61
    ixels
    -0.61
    éĸ
    -0.60
    POSITIVE LOGITS
     routed
    1.07
     rout
    0.99
     routing
    0.88
    MpServer
    0.87
    ²¾
    0.82
    ahime
    0.81
    xual
    0.79
    htaking
    0.79
    heastern
    0.77
    oute
    0.76
    Activations Density 0.019%

    No Known Activations