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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 10314
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal charges, specifically different degrees of crimes like murder and assault

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal charges and degrees of crimes

    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
    soDeliveryDate
    -0.94
    UTF
    -0.81
    natureconservancy
    -0.80
    isu
    -0.80
    imon
    -0.79
    objects
    -0.77
     Bulg
    -0.77
    sels
    -0.76
    yll
    -0.75
    bits
    -0.74
    POSITIVE LOGITS
     murder
    1.25
     manslaughter
    1.23
     felony
    1.23
     misdemeanor
    1.09
     arson
    1.04
     treason
    1.02
     kidnapping
    1.00
     burglary
    0.99
     blasphemy
    0.99
     aggravated
    0.96
    Activations Density 0.020%

    No Known Activations