© 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. 9455
    Prev
    Next
    INDEX
    Explanations

    instances of violent actions or crimes involving shooting and death

    oai_token-act-pair · gpt-3.5-turbo

    references to shootings and fatalities

    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
    Intern
    -0.79
    Balt
    -0.70
    Altern
    -0.68
    phil
    -0.67
    DIR
    -0.67
    arist
    -0.66
    Birth
    -0.64
    tz
    -0.64
    BN
    -0.64
    hist
    -0.64
    POSITIVE LOGITS
     spree
    0.99
     victims
    0.91
     rampage
    0.89
     victim
    0.89
     gunshots
    0.89
     detonated
    0.86
    llah
    0.85
     killings
    0.84
     gunfire
    0.84
     homicides
    0.84
    Activations Density 0.344%

    No Known Activations