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

    Neuronpedia

    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. 15988
    Prev
    Next
    INDEX
    Explanations

    titles or descriptions of professionals or experts

    oai_token-act-pair · gpt-3.5-turbo

    statements about individuals' professional affiliations or titles

    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
    isol
    -0.72
     versa
    -0.68
    ctrl
    -0.56
     overwhelming
    -0.56
     incon
    -0.55
    dogs
    -0.55
     cartridges
    -0.54
     therapy
    -0.54
     demoral
    -0.54
     asses
    -0.54
    POSITIVE LOGITS
    elaide
    0.82
     QC
    0.79
     Jr
    0.79
    tein
    0.78
     PhD
    0.72
     Sr
    0.71
     Died
    0.71
    hower
    0.71
    maxwell
    0.67
    nen
    0.67
    Activations Density 0.461%

    No Known Activations