© 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. 0-RES-JB
    11. 23280
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent and destructive acts such as killing sprees and criminal rampages

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of violent or chaotic events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tar
    -0.77
    tel
    -0.75
    oven
    -0.72
    igh
    -0.69
     toler
    -0.68
    Answer
    -0.68
    rimination
    -0.67
    cliffe
    -0.65
    Ale
    -0.65
    ect
    -0.63
    POSITIVE LOGITS
     spree
    3.44
     rampage
    2.43
     binge
    2.12
     frenzy
    1.76
     blitz
    1.69
     reckless
    1.48
     risky
    1.35
     Rampage
    1.19
     gamble
    1.17
     flurry
    1.14
    Activations Density 0.030%

    No Known Activations