© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 9358
    Prev
    Next
    INDEX
    Explanations

    verbs related to the action of picking something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "pick" and its derivatives

    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
    brance
    -0.84
    moral
    -0.69
    itement
    -0.67
    issance
    -0.66
    acion
    -0.65
    cess
    -0.65
    Definition
    -0.65
    enture
    -0.65
    peria
    -0.65
    isSpecialOrderable
    -0.65
    POSITIVE LOGITS
    axe
    1.13
    pocket
    1.11
    eting
    0.98
    picking
    0.91
    pick
    0.90
     pick
    0.86
     axe
    0.77
    Ń·
    0.77
    ety
    0.77
    osition
    0.74
    Activations Density 0.016%

    No Known Activations