© 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. 12-RES-JB
    11. 2451
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology advancements and innovative concepts

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    advancements and challenges in technology integration within therapeutic and healthcare practices

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     CHRIST
    -0.73
     Osw
    -0.72
     Britt
    -0.71
     Volunte
    -0.70
     Rape
    -0.69
    swick
    -0.67
     Newspaper
    -0.67
    Person
    -0.67
     Malk
    -0.65
     Reverend
    -0.65
    POSITIVE LOGITS
     prototypes
    1.29
     technological
    1.27
     patents
    1.26
     silicon
    1.22
     graphene
    1.21
     technologies
    1.21
     advancements
    1.18
     DAR
    1.16
     innovation
    1.15
     innovations
    1.15
    Activations Density 0.778%

    No Known Activations