© 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. 21763
    Prev
    Next
    INDEX
    Explanations

    specific terms related to sponsorships

    oai_token-act-pair · gpt-3.5-turbo

    words related to sponsorship agreements and related 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
     pend
    -0.83
    theless
    -0.80
    otom
    -0.76
    itia
    -0.76
     contag
    -0.75
    anwhile
    -0.67
     nerv
    -0.64
    cale
    -0.63
    otomy
    -0.63
    tes
    -0.61
    POSITIVE LOGITS
    hips
    1.29
    orship
    0.94
     sponsoring
    0.94
     logos
    0.85
     sponsors
    0.84
     sponsorship
    0.83
     Spons
    0.81
    Spons
    0.79
    ions
    0.75
     sponsor
    0.75
    Activations Density 0.088%

    No Known Activations