© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2734
    Prev
    Next
    INDEX
    Explanations

    references to news articles and posts from a specific media outlet

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

    references to "Post" and its variations in the text

    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
     ens
    -0.58
     elect
    -0.57
    èª
    -0.56
     fixme
    -0.55
     clock
    -0.55
     bands
    -0.54
     Bett
    -0.54
    istered
    -0.54
    aila
    -0.53
     WHEN
    -0.53
    POSITIVE LOGITS
    greSQL
    1.33
    gres
    1.20
    doctoral
    1.16
    erity
    1.01
    media
    1.00
    secondary
    0.96
    graduate
    0.89
    natal
    0.89
    mortem
    0.88
    mates
    0.88
    Activations Density 0.029%

    No Known Activations