© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 13771
    Prev
    Next
    INDEX
    Explanations

    targeted verbs that involve exerting influence or pressure on people or entities

    oai_token-act-pair · gpt-3.5-turbo

    verbs or phrases indicating attempts to persuade or convince others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inferred
    -0.68
    anticipated
    -0.66
    regor
    -0.65
    arij
    -0.65
     speculated
    -0.65
    Reviewed
    -0.64
     hypothesized
    -0.64
    planned
    -0.64
     encountering
    -0.63
    alach
    -0.62
    POSITIVE LOGITS
     relent
    1.25
     surrender
    1.16
     relinqu
    1.01
     acquies
    0.99
     comply
    0.99
     concede
    0.97
     divul
    0.96
     accept
    0.95
     cough
    0.95
     confess
    0.95
    Activations Density 0.226%

    No Known Activations