© 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 EvalsExportsinterp-engineNEWAPI 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. 1-RES-JB
    11. 8519
    Prev
    Next
    INDEX
    Explanations

    phrases related to drawing or gathering attention

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "drew."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aging
    -0.73
    izable
    -0.71
    erning
    -0.66
     [+]
    -0.65
    ocating
    -0.65
     Alley
    -0.64
    yond
    -0.64
    ability
    -0.64
    lining
    -0.64
    ency
    -0.63
    POSITIVE LOGITS
    nesday
    0.98
    ĸļ
    0.87
     tremend
    0.81
    EStream
    0.81
     teasp
    0.77
    hers
    0.77
    ourgeois
    0.75
    ovych
    0.75
     Wem
    0.74
    byss
    0.74
    Activations Density 0.167%

    No Known Activations