© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 250
    Prev
    Next
    INDEX
    Explanations

    details related to crime scenes and police investigations

    oai_token-act-pair · gpt-3.5-turbo

    narratives involving crime and violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -)
    -0.61
     translations
    -0.60
     learnt
    -0.60
     Journals
    -0.59
     quotes
    -0.59
    )!
    -0.59
     AMERICA
    -0.58
     endeavour
    -0.58
     resolutions
    -0.57
     concise
    -0.57
    POSITIVE LOGITS
     burglary
    0.79
    girlfriend
    0.73
    angering
    0.71
     intruder
    0.71
     intoxicated
    0.71
     burgl
    0.71
     suspic
    0.70
    illance
    0.69
     robbery
    0.66
     juveniles
    0.65
    Activations Density 0.972%

    No Known Activations