© 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. 10-RES-JB
    11. 4883
    Prev
    Next
    INDEX
    Explanations

    numeric values with associated units or measurements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    biz
    -0.70
    Enlarge
    -0.70
    cellaneous
    -0.68
    IQ
    -0.64
    quiet
    -0.64
    REF
    -0.62
    ucc
    -0.62
    istries
    -0.62
    mere
    -0.62
    WE
    -0.61
    POSITIVE LOGITS
     each
    1.15
     the
    0.92
     your
    0.91
     course
    0.84
     any
    0.81
     whichever
    0.77
     every
    0.76
     our
    0.75
     these
    0.75
     whoever
    0.74
    Activations Density 0.272%

    No Known Activations