© 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. 10-RES-JB
    11. 16512
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration or partnership

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "working with."

    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
    hood
    -0.74
    illery
    -0.72
     conclud
    -0.71
    argument
    -0.71
    mite
    -0.69
    nery
    -0.68
    claimer
    -0.68
     "$:/
    -0.68
    thing
    -0.67
     teasp
    -0.67
    POSITIVE LOGITS
     partners
    1.08
     counterparts
    1.07
     colleagues
    1.05
     collaborators
    0.99
     representatives
    0.98
     suppliers
    0.93
    stood
    0.92
     others
    0.91
     prosecutors
    0.89
     stakeholders
    0.89
    Activations Density 0.116%

    No Known Activations