© 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. 11-RES-JB
    11. 6040
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "Without"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating absence or lack of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Appears
    -0.85
    late
    -0.80
    lish
    -0.74
    ortment
    -0.72
    lator
    -0.70
    ounce
    -0.68
    des
    -0.66
    oled
    -0.65
    chet
    -0.64
    sometimes
    -0.64
    POSITIVE LOGITS
     doubt
    1.23
     exception
    1.19
     hesitation
    1.15
     exaggeration
    1.00
     mentioning
    0.96
     knowing
    0.91
     recourse
    0.90
     adequate
    0.88
     Borders
    0.88
     fail
    0.85
    Activations Density 0.048%

    No Known Activations