© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RES-JB
    11. 311
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a person named Mar

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gearing
    -0.69
     bargaining
    -0.66
     similar
    -0.65
     nest
    -0.63
     growing
    -0.61
     pree
    -0.61
     accelerated
    -0.61
     tray
    -0.60
     reserved
    -0.60
     depos
    -0.60
    POSITIVE LOGITS
    lene
    1.29
    ques
    1.28
    riages
    1.24
    cell
    1.22
    quez
    1.20
    ÃŃa
    1.14
    ussia
    1.13
    coni
    1.11
    ibel
    1.10
    lon
    1.10
    Activations Density 0.018%

    No Known Activations