© 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. 10510
    Prev
    Next
    INDEX
    Explanations

    references to what individuals are currently doing or their current status

    oai_token-act-pair · gpt-3.5-turbo

    the word "currently."

    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
     Geh
    -0.71
    child
    -0.69
    anos
    -0.65
    onal
    -0.64
     Hits
    -0.64
    stice
    -0.64
     Sco
    -0.63
    ribution
    -0.62
    pled
    -0.62
    ger
    -0.62
    POSITIVE LOGITS
     underway
    1.00
     undergoing
    0.98
     residing
    0.92
     slated
    0.88
     inactive
    0.84
     employed
    0.84
     logged
    0.83
     scheduled
    0.83
     stationed
    0.82
     deployed
    0.82
    Activations Density 0.022%

    No Known Activations