© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 273
    Prev
    Next
    INDEX
    Explanations

    violent actions and threats involving physical harm

    oai_token-act-pair · gpt-3.5-turbo

    violent or aggressive actions and their consequences

    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
     Advis
    -0.76
     Advisory
    -0.66
    WARN
    -0.64
    uggest
    -0.64
    ":["
    -0.64
     Nationals
    -0.63
    adv
    -0.60
    BIL
    -0.59
    eret
    -0.58
    iola
    -0.58
    POSITIVE LOGITS
     alive
    1.28
     senseless
    1.05
     throats
    0.96
     limb
    0.92
     whole
    0.91
     corpses
    0.91
     merciless
    0.90
     corpse
    0.90
     Alive
    0.86
     utterly
    0.86
    Activations Density 0.324%

    No Known Activations