© 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. 1-RES-JB
    11. 5376
    Prev
    Next
    INDEX
    Explanations

    words related to illegal activities, specifically fraud and blackmail

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with fraud and deceptive practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cule
    -0.70
     mitochondrial
    -0.66
     absence
    -0.65
    âĿ
    -0.62
    çĦ
    -0.61
     custody
    -0.60
    ixed
    -0.60
     stride
    -0.60
     Asheville
    -0.59
     sar
    -0.59
    POSITIVE LOGITS
    raud
    1.64
    ulent
    1.37
    emort
    1.02
    ingly
    1.01
    interstitial
    0.97
    eering
    0.91
    ible
    0.83
    uphem
    0.81
    ulence
    0.80
    gment
    0.79
    Activations Density 0.016%

    No Known Activations