© 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. 888
    Prev
    Next
    INDEX
    Explanations

    cases or instances of criminal and violent behavior involving assault and battery

    oai_token-act-pair · gpt-3.5-turbo

    incidents and references related to battery charges and assaults

    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
    gio
    -0.80
    icz
    -0.68
    Giving
    -0.67
    edi
    -0.66
    Lot
    -0.65
    ylan
    -0.65
    izen
    -0.65
    ews
    -0.64
    eker
    -0.64
    eway
    -0.63
    POSITIVE LOGITS
     battery
    0.96
     Battery
    0.90
    attery
    0.87
    Battery
    0.84
     electrodes
    0.83
     brig
    0.82
     leveled
    0.79
     acid
    0.78
     charges
    0.76
     charger
    0.73
    Activations Density 0.010%

    No Known Activations