© 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. 4870
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features of electronic devices

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

    references to features or components associated with technology and media platforms

    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
    itized
    -0.64
    illac
    -0.63
     Pax
    -0.62
     DOI
    -0.62
     Guant
    -0.60
    creen
    -0.60
     pic
    -0.60
    etically
    -0.55
    person
    -0.55
    agonists
    -0.55
    POSITIVE LOGITS
    OSS
    0.65
    ulia
    0.65
    OSP
    0.63
    bee
    0.62
    BA
    0.59
    oss
    0.59
    inger
    0.58
    IDA
    0.57
     guiActiveUnfocused
    0.56
    uga
    0.56
    Activations Density 0.345%

    No Known Activations