© 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. 22228
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical location and actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to presence and movement in context

    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
    inals
    -0.74
    orically
    -0.71
    anmar
    -0.68
    letes
    -0.64
    rences
    -0.64
    encer
    -0.63
    eful
    -0.62
    nces
    -0.61
    rys
    -0.61
    uddle
    -0.61
    POSITIVE LOGITS
     occasions
    1.01
     behalf
    0.84
     basis
    0.83
     occasion
    0.75
     Beh
    0.73
     heels
    0.73
     pedest
    0.72
    Reloaded
    0.70
    CLASSIFIED
    0.70
     forums
    0.69
    Activations Density 0.152%

    No Known Activations