© 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. 6-RES-JB
    11. 5465
    Prev
    Next
    INDEX
    Explanations

    statements of future action or intention

    oai_token-act-pair · gpt-3.5-turbo

    the future tense of the verb "will."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Economist
    -0.69
    ruciating
    -0.65
    quickShipAvailable
    -0.64
    angled
    -0.63
     inflamm
    -0.61
    licted
    -0.61
     Whats
    -0.60
    MpServer
    -0.59
    Newsletter
    -0.58
    ECA
    -0.56
    POSITIVE LOGITS
     gladly
    1.25
     be
    0.96
     NEVER
    0.88
     definitely
    0.88
     continue
    0.87
     ende
    0.87
     never
    0.84
     happily
    0.84
    soon
    0.83
    iam
    0.80
    Activations Density 0.128%

    No Known Activations