© 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. 8-RES-JB
    11. 11549
    Prev
    Next
    INDEX
    Explanations

    verbs indicating action or intention

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a call to action or urging movement towards a goal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rolled
    -0.62
     Recorded
    -0.59
    rolled
    -0.58
     Updated
    -0.57
     largeDownload
    -0.57
     averages
    -0.56
    listed
    -0.55
     stacks
    -0.55
     covers
    -0.55
     rolls
    -0.55
    POSITIVE LOGITS
    ilet
    1.23
     maximize
    1.16
     ensure
    1.14
     achieve
    1.12
    ggles
    1.10
     avoid
    1.09
     minimize
    1.05
    iling
    1.04
     begin
    1.03
     undertake
    1.01
    Activations Density 0.361%

    No Known Activations