© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12645
    Prev
    Next
    INDEX
    Explanations

    instances where the concept of 'never' is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "never"

    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
    amazon
    -0.67
    stall
    -0.60
    ERAL
    -0.60
     Archive
    -0.60
     Compass
    -0.59
     Brilliant
    -0.59
     Celebration
    -0.58
    UME
    -0.56
    Tips
    -0.56
     RTX
    -0.56
    POSITIVE LOGITS
    theless
    1.30
     been
    1.29
    been
    1.27
     gotten
    1.22
     heard
    1.17
     tasted
    1.15
     seen
    1.15
     encountered
    1.15
     hesitated
    1.12
     interacted
    1.11
    Activations Density 0.040%

    No Known Activations