© 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. 10454
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to colonization and its historical impacts

    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
     suggestion
    -0.54
     motivational
    -0.54
     ego
    -0.53
     fuzz
    -0.50
    oyal
    -0.49
    idious
    -0.48
    lihood
    -0.48
    izations
    -0.48
     humility
    -0.47
     clutch
    -0.47
    POSITIVE LOGITS
     neighbouring
    0.66
     Railway
    0.65
    abouts
    0.64
    istan
    0.62
    士
    0.60
     southeastern
    0.60
    Ô
    0.60
    quartered
    0.59
     Province
    0.59
     Confederation
    0.59
    Activations Density 2.041%

    No Known Activations