© 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. 6-RES-JB
    11. 17778
    Prev
    Next
    INDEX
    Explanations

    the word "to" followed by a verb, indicating future plans or intentions

    oai_token-act-pair · gpt-3.5-turbo

    the word "to" indicating intentions or plans

    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
    quickShipAvailable
    -0.81
    lights
    -0.68
     Explan
    -0.66
     Problem
    -0.66
    ritical
    -0.65
     Canary
    -0.63
    problem
    -0.63
     Passion
    -0.61
    Problem
    -0.61
     Tracks
    -0.60
    POSITIVE LOGITS
     pursue
    1.12
     retire
    1.06
     continue
    1.04
     explore
    1.01
     revise
    1.01
     utilize
    1.01
     spend
    1.00
     propose
    1.00
     keep
    0.99
     relocate
    0.99
    Activations Density 0.097%

    No Known Activations