© 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. 10613
    Prev
    Next
    INDEX
    Explanations

    proper nouns, possibly related to politics or law

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and groups associated with political contexts

    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
    ufact
    -0.77
    vernment
    -0.72
    shire
    -0.66
     pub
    -0.62
    ô
    -0.62
    unct
    -0.62
     ende
    -0.62
    illary
    -0.61
    ooter
    -0.61
    ably
    -0.60
    POSITIVE LOGITS
    otom
    1.10
    OTUS
    0.91
     TAMADRA
    0.81
    Folder
    0.75
    ices
    0.75
    LU
    0.73
    creen
    0.73
     justices
    0.71
    å¦
    0.70
    Court
    0.68
    Activations Density 0.020%

    No Known Activations