© 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. 2-RES-JB
    11. 6404
    Prev
    Next
    INDEX
    Explanations

    methods or techniques

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Acad
    -0.62
    enda
    -0.62
     gloom
    -0.60
     Reading
    -0.59
    ership
    -0.59
    oÄŁ
    -0.59
     Costa
    -0.59
     Madden
    -0.58
     Messi
    -0.58
     Barkley
    -0.58
    POSITIVE LOGITS
    ologies
    1.10
     methods
    1.06
     method
    0.91
    method
    0.89
    krit
    0.86
    DragonMagazine
    0.83
    ologic
    0.82
    etter
    0.80
    ologically
    0.79
    hell
    0.78
    Activations Density 0.016%

    No Known Activations