© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 20364
    Prev
    Next
    INDEX
    Explanations

    phrases indicating alternatives or contrasts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the negation of something being a "zero-sum game."

    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
    uin
    -0.75
    Effects
    -0.71
    Thom
    -0.69
    scenes
    -0.68
    Edit
    -0.68
    tests
    -0.66
    Versions
    -0.66
    Links
    -0.66
    icons
    -0.66
    Anim
    -0.66
    POSITIVE LOGITS
     coincidence
    1.09
     anymore
    1.07
     dime
    0.94
     slightest
    0.93
     bother
    0.89
    verse
    0.88
     necessarily
    0.83
     bunch
    0.82
     nor
    0.81
     mere
    0.80
    Activations Density 0.084%

    No Known Activations