© 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. 4-RES-JB
    11. 22030
    Prev
    Next
    INDEX
    Explanations

    business partnerships mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "partnership."

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

    No Comments

    Negative Logits
    acco
    -0.80
    missing
    -0.75
    icted
    -0.72
    hma
    -0.72
    achers
    -0.72
    ikhail
    -0.71
    roller
    -0.71
    thia
    -0.71
    haps
    -0.71
    rollers
    -0.70
    POSITIVE LOGITS
     partner
    1.06
     partnership
    1.00
     partnerships
    0.99
     partners
    0.98
     Partnership
    0.89
     between
    0.83
     teamed
    0.82
    hips
    0.81
     collaboration
    0.78
     partnered
    0.77
    Activations Density 0.020%

    No Known Activations