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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 24153
    Prev
    Next
    INDEX
    Explanations

    terms related to nonviolent and violent actions and movements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to violence and nonviolence in social or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asus
    -0.72
    ousel
    -0.70
     Annotations
    -0.68
    oise
    -0.67
    edes
    -0.67
    gob
    -0.64
    osp
    -0.63
    bos
    -0.63
    addons
    -0.63
     Hun
    -0.63
    POSITIVE LOGITS
     nonviolent
    1.10
    violent
    1.00
    thouse
    0.73
    violence
    0.73
     disobedience
    0.72
    terday
    0.71
    0000000000000000
    0.66
    ceed
    0.64
     pacif
    0.64
    ategy
    0.63
    Activations Density 0.023%

    No Known Activations