© 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. 4-RES-JB
    11. 4861
    Prev
    Next
    INDEX
    Explanations

    action verbs related to planning or execution

    oai_token-act-pair · gpt-3.5-turbo

    infinitive verbs that express intention or purpose

    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
     handles
    -0.67
     airs
    -0.65
     HD
    -0.63
     Appears
    -0.62
     reperto
    -0.59
     warranties
    -0.59
     reacts
    -0.59
     slips
    -0.59
    quickShipAvailable
    -0.59
     enjoys
    -0.58
    POSITIVE LOGITS
    othy
    0.95
    lling
    0.90
    lled
    0.89
    pless
    0.85
    avering
    0.81
     beware
    0.79
    define
    0.79
    adies
    0.79
     provide
    0.78
     treat
    0.78
    Activations Density 0.184%

    No Known Activations