© 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. 8-RES-JB
    11. 3062
    Prev
    Next
    INDEX
    Explanations

    criminal activities and legal terms, including various crimes and charges

    oai_token-act-pair · gpt-3.5-turbo

    terms related to violent crimes and weapons offenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulously
    -0.74
     trillions
    -0.68
    NUM
    -0.68
    hower
    -0.67
    NetMessage
    -0.64
    Dialog
    -0.62
    ucci
    -0.62
     Krugman
    -0.61
    SAM
    -0.60
     billions
    -0.60
    POSITIVE LOGITS
     lawful
    0.95
     unlawfully
    0.93
     firearm
    0.90
     unlawful
    0.90
     felon
    0.88
     felony
    0.87
     intoxicated
    0.86
     indecent
    0.82
     perjury
    0.80
     underage
    0.80
    Activations Density 0.314%

    No Known Activations