© 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. 8-RES-JB
    11. 1157
    Prev
    Next
    INDEX
    Explanations

    references to newspaper names and titles

    oai_token-act-pair · gpt-3.5-turbo

    references to a particular newspaper or media outlet

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afety
    -0.86
    ashtra
    -0.71
    jab
    -0.71
    azard
    -0.71
    iard
    -0.68
     condu
    -0.65
    enhagen
    -0.65
    utical
    -0.64
    tery
    -0.64
    Topic
    -0.63
    POSITIVE LOGITS
     Savior
    0.73
    Irish
    0.69
    Sax
    0.69
    ¥µ
    0.69
    icket
    0.66
     Gleaming
    0.64
    otos
    0.64
     brightest
    0.63
     Strip
    0.63
    Legendary
    0.62
    Activations Density 0.115%

    No Known Activations