© 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. 2686
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a point to remember or keep in mind

    oai_token-act-pair · gpt-3.5-turbo

    phrases urging readers to stay informed or pay attention

    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
    iliary
    -0.79
    ode
    -0.77
    DragonMagazine
    -0.71
    NetMessage
    -0.66
    RES
    -0.64
    ointed
    -0.64
    ohydrate
    -0.64
    omas
    -0.62
    éĹ
    -0.62
    ELF
    -0.61
    POSITIVE LOGITS
     tabs
    0.91
     Calm
    0.87
     track
    0.86
     vigil
    0.82
     scrolling
    0.79
     tuned
    0.78
     kosher
    0.77
     vigilance
    0.76
    akes
    0.76
     calm
    0.75
    Activations Density 0.031%

    No Known Activations