© 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. 1-RES-JB
    11. 8579
    Prev
    Next
    INDEX
    Explanations

    mentions of news-related terms, particularly related to anchors or news channels

    oai_token-act-pair · gpt-3.5-turbo

    references to news anchors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ensation
    -0.88
    wagen
    -0.78
    STEM
    -0.76
    govtrack
    -0.74
    yles
    -0.71
    ordan
    -0.70
    esa
    -0.69
    axies
    -0.68
    plets
    -0.68
    ccess
    -0.67
    POSITIVE LOGITS
     anchor
    1.46
     anch
    1.33
     anchors
    1.24
     anchored
    1.13
     Anch
    0.87
    orage
    0.79
     filler
    0.77
     enchant
    0.76
     tenant
    0.75
     reefs
    0.74
    Activations Density 0.006%

    No Known Activations