© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 7560
    Prev
    Next
    INDEX
    Explanations

    locations and activities related to law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or actions involving authorities or official institutions

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

    No Comments

    Negative Logits
     depends
    -0.68
     Miliband
    -0.61
     Fail
    -0.60
     Draco
    -0.59
     Darkness
    -0.57
     quo
    -0.56
     Pastebin
    -0.56
    lihood
    -0.56
    onom
    -0.55
     Pog
    -0.55
    POSITIVE LOGITS
     respectively
    0.95
    interstitial
    0.69
    çͰ
    0.60
    acus
    0.59
    zona
    0.58
    yssey
    0.57
    adin
    0.56
    ampions
    0.55
    ospons
    0.54
    itled
    0.54
    Activations Density 2.675%

    No Known Activations