© 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. 12969
    Prev
    Next
    INDEX
    Explanations

    mentions of products or services in the context of positive experiences or gratitude

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "and" in various contexts

    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
    Contents
    -0.68
    FIG
    -0.66
    ocative
    -0.66
    Enlarge
    -0.65
    letes
    -0.65
    grades
    -0.64
    elle
    -0.64
    FILE
    -0.62
     Himself
    -0.62
    tnc
    -0.62
    POSITIVE LOGITS
     am
    1.19
     intend
    1.12
     haven
    1.11
     believe
    1.07
     adore
    1.05
     have
    1.02
     want
    1.01
     I
    1.00
     appreciate
    0.99
     wish
    0.97
    Activations Density 0.212%

    No Known Activations