© 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. 3-RES-JB
    11. 4453
    Prev
    Next
    INDEX
    Explanations

    prepositions and determiners preceding nouns

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating location or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    daq
    -0.87
    DERR
    -0.80
    GBT
    -0.80
    ONEY
    -0.79
    PATH
    -0.75
    Fax
    -0.71
    mone
    -0.71
    DEV
    -0.70
    PLA
    -0.70
    Ire
    -0.69
    POSITIVE LOGITS
     nutshell
    0.86
     Decay
    0.78
     Aging
    0.73
     Removal
    0.73
    pires
    0.73
     Scene
    0.70
     Rev
    0.68
     Sight
    0.64
     Broken
    0.64
     Murd
    0.64
    Activations Density 1.029%

    No Known Activations