© 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. 3-RES-JB
    11. 15848
    Prev
    Next
    INDEX
    Explanations

    words related to abstention or refraining from something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to abstention or abstinence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spur
    -0.79
     Fitz
    -0.78
    Reviewer
    -0.76
    videos
    -0.70
     Waterloo
    -0.70
     Stevens
    -0.69
     guiActiveUnfocused
    -0.69
    ãĤ¨ãĥ«
    -0.68
     Sisters
    -0.67
     Tycoon
    -0.67
    POSITIVE LOGITS
     abst
    1.14
    iencies
    0.94
    ention
    0.91
    aye
    0.90
    ree
    0.85
    arians
    0.81
    inance
    0.79
     filib
    0.78
    ensible
    0.78
    inent
    0.77
    Activations Density 0.007%

    No Known Activations