© 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. 2582
    Prev
    Next
    INDEX
    Explanations

    details related to criminal incidents, such as suspects, weapons, and attacks

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

    references to bombs and explosive events

    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
    HCR
    -1.07
     Cosponsors
    -0.91
    vier
    -0.83
    River
    -0.83
    emale
    -0.83
    ivia
    -0.82
    MpServer
    -0.77
     Geral
    -0.77
    irez
    -0.77
    ctuary
    -0.76
    POSITIVE LOGITS
     deton
    2.19
     detonated
    2.13
     explosives
    2.05
     bombs
    2.01
     bomb
    1.97
     explosions
    1.80
     explosion
    1.73
     Explos
    1.72
     Bomb
    1.71
    Bomb
    1.70
    Activations Density 0.493%

    No Known Activations