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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 12535
    Prev
    Next
    INDEX
    Explanations

    words related to criminal activities such as mugging and assault

    oai_token-act-pair · gpt-3.5-turbo

    references to mugging incidents or related violent acts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ×Ļ×
    -0.75
    Domin
    -0.71
    edient
    -0.71
    IGH
    -0.70
     Doctrine
    -0.69
    ipher
    -0.68
    peak
    -0.68
    ISION
    -0.68
    cision
    -0.66
     Virgin
    -0.66
    POSITIVE LOGITS
     mug
    1.17
    gers
    1.10
    ging
    1.00
    shots
    0.99
    ger
    0.96
    shot
    0.94
    atures
    0.87
    ged
    0.86
     Mug
    0.82
    glers
    0.81
    Activations Density 0.007%

    No Known Activations