© 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. 12783
    Prev
    Next
    INDEX
    Explanations

    descriptions related to violent acts, specifically murder

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "murdered."

    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
    ffic
    -0.81
    rium
    -0.79
    aque
    -0.79
    Scot
    -0.79
    issue
    -0.76
    alter
    -0.73
     CLSID
    -0.70
    por
    -0.69
    gran
    -0.69
    Champ
    -0.68
    POSITIVE LOGITS
     murdered
    0.99
     slain
    0.85
     murdering
    0.83
     spree
    0.83
     murders
    0.79
    ÃįÃį
    0.77
     killings
    0.76
    nesday
    0.76
     adolesc
    0.74
    ãĥĥãĥī
    0.73
    Activations Density 0.029%

    No Known Activations