© 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. 3285
    Prev
    Next
    INDEX
    Explanations

    events or gatherings that bring people together

    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
    asus
    -0.66
    bal
    -0.65
     deficiency
    -0.62
    bilt
    -0.62
    balance
    -0.61
    odor
    -0.60
     descriptor
    -0.60
     converter
    -0.59
     knob
    -0.59
    shield
    -0.58
    POSITIVE LOGITS
    hips
    1.35
    hops
    1.31
    chool
    1.17
    hare
    1.16
    paces
    1.15
     involving
    1.10
     conducted
    1.08
     abroad
    1.06
    creen
    1.04
    pring
    1.02
    Activations Density 0.296%

    No Known Activations