© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7363
    Prev
    Next
    INDEX
    Explanations

    words related to physical sensations or actions that involve forceful impact or pressure

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "smog" and its variations

    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
    DragonMagazine
    -0.96
     Vanguard
    -0.75
     Defenders
    -0.66
    quickShipAvailable
    -0.65
    EMENT
    -0.64
     Scrib
    -0.64
    HCR
    -0.64
     Fargo
    -0.63
     Guantanamo
    -0.63
     McConnell
    -0.62
    POSITIVE LOGITS
    oky
    1.13
    ugg
    0.99
    itten
    0.99
    attering
    0.96
    ashed
    0.96
    elly
    0.93
    udge
    0.91
    acking
    0.90
    ashing
    0.89
    ithing
    0.89
    Activations Density 0.009%

    No Known Activations