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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 6491
    Prev
    Next
    INDEX
    Explanations

    words that are dedicated to honoring or emphasizing something within a sentence

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FINE
    -0.75
    hyde
    -0.75
    LEASE
    -0.70
    EStream
    -0.69
    tainment
    -0.65
    GROUND
    -0.64
     Mellon
    -0.64
     duplicate
    -0.64
     Governors
    -0.63
     Wikileaks
    -0.62
    POSITIVE LOGITS
    igm
    1.10
    igma
    1.06
    arin
    1.06
    arah
    1.03
    ink
    1.02
    ixties
    0.96
    ams
    0.94
    outher
    0.94
    ources
    0.93
    assy
    0.93
    Activations Density 0.042%

    No Known Activations