© 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. 6415
    Prev
    Next
    INDEX
    Explanations

    time-related expressions with "or so" indicating an approximate duration

    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
    cture
    -0.64
    undrum
    -0.63
    adelphia
    -0.60
    tz
    -0.59
    irement
    -0.57
     Kaplan
    -0.57
    ename
    -0.56
    ocaust
    -0.55
    rez
    -0.54
    ortium
    -0.54
    POSITIVE LOGITS
     alike
    1.52
     thereof
    1.11
     respectively
    1.10
     accordingly
    1.06
     thereafter
    1.01
     versa
    0.98
     thereto
    0.94
     therein
    0.90
     afterward
    0.83
     afterwards
    0.83
    Activations Density 3.246%

    No Known Activations