© 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. 21431
    Prev
    Next
    INDEX
    Explanations

    violence-related actions involving physical harm

    oai_token-act-pair · gpt-3.5-turbo

    references to violent actions and weaponry

    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
    igne
    -0.80
    vana
    -0.75
     Resp
    -0.74
    batch
    -0.73
    parency
    -0.71
    200000
    -0.69
    DragonMagazine
    -0.69
     Relax
    -0.67
    glers
    -0.66
    RGB
    -0.66
    POSITIVE LOGITS
     knives
    1.30
     hamm
    1.19
     spears
    1.19
     stones
    1.17
     punches
    1.15
     projectiles
    1.15
     hammer
    1.15
     sticks
    1.11
     fists
    1.11
     rocks
    1.09
    Activations Density 0.170%

    No Known Activations