© 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. 4-RES-JB
    11. 16899
    Prev
    Next
    INDEX
    Explanations

    words related to controversial claims or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    claims or assertions related to various topics

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

    No Comments

    Negative Logits
    sonian
    -0.66
    cellaneous
    -0.63
    iasm
    -0.61
     alleges
    -0.58
     Increases
    -0.56
     VIDEOS
    -0.55
    gae
    -0.55
    student
    -0.55
     begs
    -0.55
    lins
    -0.55
    POSITIVE LOGITS
     outweigh
    0.65
     solely
    0.63
     unacceptable
    0.62
     unfairly
    0.62
     genuine
    0.62
    Jews
    0.60
     constitutionally
    0.60
     sufficiently
    0.59
     legitimately
    0.59
     outwe
    0.59
    Activations Density 1.767%

    No Known Activations