© 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. 5027
    Prev
    Next
    INDEX
    Explanations

    phrases related to political debates and issues

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

    patterns of text related to continuous or ongoing events

    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
    asonic
    -0.88
    flo
    -0.85
    pher
    -0.81
    otin
    -0.81
    posing
    -0.78
    milo
    -0.77
    cohol
    -0.77
    pha
    -0.77
    oqu
    -0.77
    pi
    -0.76
    POSITIVE LOGITS
    UES
    1.51
    UE
    1.47
    ues
    1.17
    IONS
    1.05
    ĭ
    0.95
    ION
    0.92
    ue
    0.87
    OME
    0.87
    ĩ
    0.86
    ENT
    0.85
    Activations Density 0.168%

    No Known Activations