© 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. 4-RES-JB
    11. 10138
    Prev
    Next
    INDEX
    Explanations

    weapons and violent actions in a text

    oai_token-act-pair · gpt-3.5-turbo

    objects and tools associated with violence or injury

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

    No Comments

    Negative Logits
    Appearance
    -0.88
     Inher
    -0.84
    Pand
    -0.83
    DragonMagazine
    -0.80
     Interstellar
    -0.80
     Spiel
    -0.79
    Climate
    -0.77
    Reviewer
    -0.73
    soDeliveryDate
    -0.70
    imester
    -0.68
    POSITIVE LOGITS
     grenade
    0.92
     grenades
    0.91
     cane
    0.85
     severed
    0.85
     handcuffed
    0.85
     explosives
    0.84
     plaster
    0.83
     handcuffs
    0.82
     taped
    0.82
     buttocks
    0.82
    Activations Density 0.548%

    No Known Activations