© 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. 0-RES-JB
    11. 9735
    Prev
    Next
    INDEX
    Explanations

    phrases related to surrendering or giving up control

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "surrender" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stud
    -0.74
    Fact
    -0.64
     Influ
    -0.63
    conom
    -0.61
    lot
    -0.60
     researched
    -0.60
     Orth
    -0.60
     Jobs
    -0.59
    ["
    -0.59
     Booster
    -0.59
    POSITIVE LOGITS
     surrender
    3.95
     surrendered
    2.78
     relinqu
    1.96
     capit
    1.76
     forfeit
    1.51
     conced
    1.41
     forfe
    1.31
     retreat
    1.29
     resignation
    1.22
     acquies
    1.19
    Activations Density 0.023%

    No Known Activations