Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 3243
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreements or negotiations

    oai_token-act-pair · gpt-3.5-turbo

    instances of agreements or commitments made by parties

    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
    uther
    -0.80
    vantage
    -0.77
    ortunate
    -0.74
    anted
    -0.69
    acity
    -0.69
    /-
    -0.68
    worldly
    -0.68
    clips
    -0.67
    oward
    -0.67
    é»Ĵ
    -0.66
    POSITIVE LOGITS
     cooperate
    1.24
     waive
    1.23
     abide
    1.19
     participate
    1.16
     settle
    1.14
     postpone
    1.07
     negotiate
    1.05
     collaborate
    1.05
     forfeit
    1.04
     undertake
    1.03
    Activations Density 0.047%

    No Known Activations