© 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. 9-RES-JB
    11. 17131
    Prev
    Next
    INDEX
    Explanations

    financial crimes and fraudulent activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of fraud and related criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odox
    -0.86
    ļéĨĴ
    -0.81
    optim
    -0.74
    ohm
    -0.74
    finished
    -0.73
     sacrificed
    -0.72
    oeuv
    -0.72
    istine
    -0.72
     Eternity
    -0.71
     glide
    -0.70
    POSITIVE LOGITS
     prosecutions
    1.36
     incidents
    1.29
     perpetrators
    1.26
     arrests
    1.24
     crimes
    1.24
     crackdown
    1.20
     criminal
    1.18
     offenders
    1.17
     offences
    1.15
     criminals
    1.15
    Activations Density 0.987%

    No Known Activations