© 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. 4739
    Prev
    Next
    INDEX
    Explanations

    items related to merchandise or products, specifically limited edition collectibles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to tattoos and body art

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    cube
    -0.77
     Cluster
    -0.76
     CPC
    -0.70
    apeake
    -0.70
    edy
    -0.70
     Galile
    -0.68
    renheit
    -0.67
     Bernstein
    -0.67
    erate
    -0.66
    dule
    -0.65
    POSITIVE LOGITS
     tattoos
    2.50
     tattoo
    2.49
     Tatt
    2.31
     tatt
    1.53
     ink
    1.35
     pier
    1.30
     Ink
    1.21
     scars
    1.19
     piercing
    1.17
     shave
    1.12
    Activations Density 0.252%

    No Known Activations