© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22612
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions done without permission or consent

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "without" and phrases implying lack or absence

    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
    late
    -0.80
    raq
    -0.78
    lated
    -0.68
    soon
    -0.68
    lyak
    -0.68
    =-=-=-=-=-=-=-=-
    -0.68
    berman
    -0.67
    onen
    -0.66
    Ranked
    -0.66
    aez
    -0.65
    POSITIVE LOGITS
     bothering
    1.23
     realizing
    1.19
     noticing
    1.17
     hesitation
    1.17
     mentioning
    1.07
     knowing
    1.06
     blinking
    1.04
     specifying
    1.03
     interruption
    1.03
     exception
    1.00
    Activations Density 0.049%

    No Known Activations