© 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. 4399
    Prev
    Next
    INDEX
    Explanations

    web links

    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
     264
    -0.82
     Turner
    -0.79
    tera
    -0.76
     =================================
    -0.74
     266
    -0.73
     Âł Âł Âł Âł Âł Âł Âł Âł
    -0.72
     Palmer
    -0.71
     272
    -0.70
    264
    -0.68
    594
    -0.68
    POSITIVE LOGITS
    h
    1.29
    adh
    1.05
    hest
    1.01
    hin
    0.99
    hr
    0.98
    hw
    0.97
    eh
    0.97
    hn
    0.95
    hart
    0.94
    hatt
    0.93
    Activations Density 0.206%

    No Known Activations