© 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. 9-RES-JB
    11. 22689
    Prev
    Next
    INDEX
    Explanations

    phrases related to observation or understanding

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing observation or perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nor
    -0.82
    due
    -0.80
    FIR
    -0.70
    lique
    -0.70
    utenberg
    -0.69
    iosyn
    -0.68
    adh
    -0.68
     confir
    -0.68
    uala
    -0.68
    aith
    -0.68
    POSITIVE LOGITS
     yourselves
    1.00
     yourself
    0.97
     me
    0.70
     billboards
    0.70
     guys
    0.68
     why
    0.67
     everywhere
    0.67
    dust
    0.66
     here
    0.64
     what
    0.63
    Activations Density 0.081%

    No Known Activations