© 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. 3-RES-JB
    11. 21032
    Prev
    Next
    INDEX
    Explanations

    phrases indicating deception or false information

    oai_token-act-pair · gpt-3.5-turbo

    terms related to deception or misrepresentation in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mun
    -0.71
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.71
    itar
    -0.66
    foreseen
    -0.66
    dain
    -0.63
    ube
    -0.63
    Interstitial
    -0.62
    area
    -0.61
    DAY
    -0.61
    %"
    -0.61
    POSITIVE LOGITS
    ingly
    1.20
     misled
    1.13
     mislead
    1.12
     misleading
    1.02
     deceive
    1.00
     deceived
    0.93
     dece
    0.88
     misrepresent
    0.84
    fully
    0.83
     confuse
    0.81
    Activations Density 0.014%

    No Known Activations