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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-RES-JB
    6. 13151
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreements or settlements between parties

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating agreements, deals, or consensus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     followed
    -0.75
     preceded
    -0.71
    watching
    -0.68
     arose
    -0.67
     endured
    -0.66
     sake
    -0.65
    sbm
    -0.64
     transpired
    -0.63
     existed
    -0.62
     ensued
    -0.62
    POSITIVE LOGITS
     heights
    1.05
     conclusion
    0.97
     conclusions
    0.89
     milestone
    0.89
     plateau
    0.86
     bounds
    0.86
     pinnacle
    0.85
     threshold
    0.81
     depths
    0.80
    limit
    0.80
    Activations Density 0.088%

    No Known Activations