© 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. 10-RES-JB
    11. 12047
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent acts and their victims

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idth
    -0.74
    Applic
    -0.68
    FML
    -0.68
    RET
    -0.65
     cancell
    -0.65
    osterone
    -0.61
    Balt
    -0.61
    ãĥ¼ãĥĨ
    -0.60
    WARN
    -0.60
    Īè
    -0.59
    POSITIVE LOGITS
     unarmed
    1.04
     innoc
    1.00
     innocent
    0.98
     indiscrim
    0.91
     senseless
    0.91
     bystanders
    0.87
     fleeing
    0.86
     peacefully
    0.86
     hostage
    0.83
     hostages
    0.81
    Activations Density 0.175%

    No Known Activations