© 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. 2-RES-JB
    11. 12764
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or items

    oai_token-act-pair · gpt-3.5-turbo

    references to specific items or entities marked by the word "these."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pless
    -0.74
    ppe
    -0.74
    orst
    -0.71
    esty
    -0.70
    achus
    -0.69
    ilet
    -0.67
    eling
    -0.66
    hood
    -0.64
    onis
    -0.63
    ë
    -0.63
    POSITIVE LOGITS
     particular
    0.78
     newfound
    0.78
     fellows
    0.75
     findings
    0.72
     kinds
    0.72
     latter
    0.69
     sorts
    0.67
     elusive
    0.66
     nifty
    0.65
     pesky
    0.65
    Activations Density 0.058%

    No Known Activations