© 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. 17173
    Prev
    Next
    INDEX
    Explanations

    verbs related to assertive or commanding actions

    oai_token-act-pair · gpt-3.5-turbo

    words associated with actions and responsibilities

    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
    pmwiki
    -0.71
    aceae
    -0.62
    soDeliveryDate
    -0.62
    DragonMagazine
    -0.60
    rs
    -0.59
    microsoft
    -0.59
    BuyableInstoreAndOnline
    -0.59
    plom
    -0.58
    rag
    -0.57
    ija
    -0.56
    POSITIVE LOGITS
    ulate
    0.92
    uate
    0.88
    roman
    0.79
    olate
    0.78
    strate
    0.74
     Flare
    0.72
    matically
    0.71
    imize
    0.68
    lessly
    0.66
    ISE
    0.64
    Activations Density 0.691%

    No Known Activations