© 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. 1-RES-JB
    11. 11383
    Prev
    Next
    INDEX
    Explanations

    information sources or references indicated by "via"

    oai_token-act-pair · gpt-3.5-turbo

    references to the source of information or content attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atter
    -0.71
    arks
    -0.71
    ancies
    -0.69
    schild
    -0.67
     retard
    -0.67
     impression
    -0.66
    ergy
    -0.63
    uster
    -0.63
     seas
    -0.62
     boundary
    -0.62
    POSITIVE LOGITS
    via
    1.43
    Via
    0.95
     Via
    0.95
     Brune
    0.85
    rolet
    0.85
     PubMed
    0.75
    ãĥ¼ãĥĨãĤ£
    0.75
     via
    0.74
    license
    0.72
     Shutterstock
    0.72
    Activations Density 0.005%

    No Known Activations