© 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. 2-RES-JB
    11. 24087
    Prev
    Next
    INDEX
    Explanations

    violent actions and criminal events

    oai_token-act-pair · gpt-3.5-turbo

    elements related to violent incidents and criminal activities

    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
    akeru
    -0.69
     Architects
    -0.64
    channelAvailability
    -0.63
    erenn
    -0.63
    arenthood
    -0.62
     Flavoring
    -0.60
    hematic
    -0.60
    rosso
    -0.60
    Reviewer
    -0.60
    natureconservancy
    -0.59
    POSITIVE LOGITS
     altercation
    0.88
     barric
    0.85
     gunman
    0.79
     kios
    0.78
    bag
    0.72
     assailant
    0.72
     checkpoint
    0.71
     gunfire
    0.70
     sergeant
    0.70
     buggy
    0.70
    Activations Density 1.103%

    No Known Activations