© 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. 4-RES-JB
    11. 22219
    Prev
    Next
    INDEX
    Explanations

    words related to deception or trickery

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to deception and being misled

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

    No Comments

    Negative Logits
    area
    -0.68
    oran
    -0.65
    Occup
    -0.64
    mun
    -0.61
    Interstitial
    -0.60
    foreseen
    -0.59
    capacity
    -0.59
    empl
    -0.57
    Pain
    -0.55
     grievances
    -0.55
    POSITIVE LOGITS
     deceive
    1.04
     deceived
    1.00
     fooled
    0.99
    ingly
    0.96
     gull
    0.91
    eering
    0.85
    ulent
    0.85
     tricked
    0.84
     confuse
    0.81
     unwitting
    0.81
    Activations Density 0.033%

    No Known Activations