© 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. 10-RES-JB
    11. 4625
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making or asserting beliefs

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs and phrases indicating potential actions or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iHUD
    -0.92
    Vis
    -0.79
    VERTISEMENT
    -0.78
     Caller
    -0.76
    scenes
    -0.76
     Hours
    -0.73
    VIDEO
    -0.72
    enna
    -0.72
    Days
    -0.71
    pict
    -0.70
    POSITIVE LOGITS
     abolish
    1.44
     legisl
    1.44
     regulate
    1.29
     legalize
    1.27
     impose
    1.27
     incarcer
    1.22
     eliminate
    1.22
     criticize
    1.21
     propose
    1.20
     liberate
    1.19
    Activations Density 0.338%

    No Known Activations