© 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. 18499
    Prev
    Next
    INDEX
    Explanations

    instances where someone does a good, outstanding, or great job

    oai_token-act-pair · gpt-3.5-turbo

    phrases that assess the quality or effectiveness of actions or performances

    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
     Arri
    -0.71
     fears
    -0.69
     Cursed
    -0.68
     Courage
    -0.67
    went
    -0.65
    FontSize
    -0.65
     Made
    -0.64
     Returning
    -0.64
     Torn
    -0.63
     Heard
    -0.63
    POSITIVE LOGITS
     homework
    0.86
     grunt
    0.86
     thing
    0.80
     job
    0.77
     justice
    0.76
     laundry
    0.74
     deed
    0.74
    judicial
    0.72
     chores
    0.71
     darn
    0.68
    Activations Density 0.119%

    No Known Activations