© 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. 11-RES-JB
    11. 9888
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent actions or incidents

    oai_token-act-pair · gpt-3.5-turbo

    references to violent incidents and statistics related to crime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -1.02
    ledge
    -0.80
    affer
    -0.77
    ãĤ¨
    -0.75
    ractive
    -0.72
    AH
    -0.71
    ategic
    -0.70
    Position
    -0.70
    ETF
    -0.70
    DIS
    -0.69
    POSITIVE LOGITS
     northeastern
    0.94
     cities
    0.89
     robberies
    0.87
     Northeast
    0.87
     southeastern
    0.86
     mosques
    0.86
     southern
    0.85
     northwestern
    0.84
     southwestern
    0.84
     downtown
    0.84
    Activations Density 0.228%

    No Known Activations