© 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. 11-RES-JB
    11. 7815
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration or partnership

    oai_token-act-pair · gpt-3.5-turbo

    instances of joining or collaboration between entities

    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
    icz
    -0.76
    bach
    -0.71
    efficiency
    -0.70
    pmwiki
    -0.66
    framework
    -0.65
    otropic
    -0.65
    anyl
    -0.64
    cember
    -0.63
    merce
    -0.62
    effic
    -0.62
    POSITIVE LOGITS
     forces
    1.54
     Forces
    1.14
     hands
    1.06
     ranks
    0.97
     together
    0.89
     us
    0.79
     dots
    0.77
     Hands
    0.77
     up
    0.72
     them
    0.72
    Activations Density 0.035%

    No Known Activations