© 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. 10-RES-JB
    11. 10649
    Prev
    Next
    INDEX
    Explanations

    phrases related to manipulation or coercion

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating coercion or manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thora
    -0.83
    DragonMagazine
    -0.74
    geist
    -0.72
    netflix
    -0.68
    tm
    -0.67
    mr
    -0.66
    ILA
    -0.64
    enery
    -0.63
    engers
    -0.63
    die
    -0.63
    POSITIVE LOGITS
     submission
    1.29
     believing
    1.23
     accepting
    1.10
     agreeing
    1.06
     becoming
    1.03
     committing
    1.02
     behaving
    1.01
     joining
    0.97
     adopting
    0.97
     signing
    0.96
    Activations Density 0.058%

    No Known Activations