© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 22820
    Prev
    Next
    INDEX
    Explanations

    phrases related to negotiations and agreements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to negotiations and legal discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mom
    -0.77
    spin
    -0.68
    stroke
    -0.64
    desktop
    -0.63
    pages
    -0.63
     CONTROL
    -0.62
     homeowner
    -0.62
     kid
    -0.61
    egg
    -0.60
    central
    -0.59
    POSITIVE LOGITS
    oti
    1.52
    otiation
    0.98
     renegoti
    0.89
    terness
    0.87
    ovan
    0.84
    ptin
    0.84
     Ng
    0.84
    eteenth
    0.83
     Jinn
    0.83
    hei
    0.82
    Activations Density 0.002%

    No Known Activations