© 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. 4418
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a significant change or contrast

    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
    ulia
    -0.78
    sels
    -0.77
    lance
    -0.76
    ITIES
    -0.75
    ulators
    -0.74
    ATURES
    -0.72
    afety
    -0.72
    itars
    -0.71
    ooks
    -0.70
    ngth
    -0.70
    POSITIVE LOGITS
     different
    0.90
     unrelated
    0.87
     hypothetical
    0.86
     fictitious
    0.86
     unrecogn
    0.85
     coherent
    0.85
     fictional
    0.85
     organic
    0.84
     functional
    0.82
     unconventional
    0.82
    Activations Density 0.081%

    No Known Activations