© 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. 24561
    Prev
    Next
    INDEX
    Explanations

    events related to political conflicts or crises

    oai_token-act-pair · gpt-3.5-turbo

    instances of statistics or references to violence and conflict

    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
    eus
    -0.77
    +++
    -0.72
    laughs
    -0.71
    lyn
    -0.70
    perture
    -0.69
    :(
    -0.69
    eur
    -0.68
    ãĤº
    -0.67
    Mods
    -0.67
    âĶĢâĶĢâĶĢâĶĢ
    -0.66
    POSITIVE LOGITS
     prompting
    1.15
     including
    0.99
     sparking
    0.95
     stemming
    0.93
     deepening
    0.89
     citing
    0.88
     noting
    0.88
     particularly
    0.88
     which
    0.88
     meanwhile
    0.87
    Activations Density 0.455%

    No Known Activations