© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 4889
    Prev
    Next
    INDEX
    Explanations

    mentions of technical details related to guitars and music equipment

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    specific technical specifications related to audio equipment

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     laund
    -0.77
    Crime
    -0.76
    §
    -0.69
     Pension
    -0.68
     Counsel
    -0.67
    "}],"
    -0.66
    votes
    -0.65
    igil
    -0.65
    vous
    -0.65
     contagious
    -0.65
    POSITIVE LOGITS
     amplifier
    1.62
     headphone
    1.58
     loudspe
    1.57
     bass
    1.48
     headphones
    1.47
     impedance
    1.41
     amps
    1.36
     acoustic
    1.36
     guitars
    1.35
     speakers
    1.34
    Activations Density 0.299%

    No Known Activations