© 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. 24284
    Prev
    Next
    INDEX
    Explanations

    phrases related to stakeholder engagement and involvement in decision-making processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stakeholders and decision-making processes

    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
    ophobic
    -0.70
    otropic
    -0.66
    flat
    -0.66
    bows
    -0.65
    thur
    -0.65
    ammers
    -0.63
    ophobia
    -0.62
    ending
    -0.61
    otrop
    -0.61
    nesia
    -0.60
    POSITIVE LOGITS
     stakeholders
    1.15
     guiActiveUn
    0.78
     stake
    0.76
     minded
    0.73
    ecided
    0.69
     involved
    0.68
     subsystem
    0.68
     collaborate
    0.67
    ashtra
    0.67
    olicy
    0.67
    Activations Density 0.022%

    No Known Activations