© 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. 1-RES-JB
    11. 8916
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Chromebook" at various intensities, with potentially higher emphasis on some references

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Chromebook" and related terms

    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
    esthetic
    -0.87
    Reviewer
    -0.74
    nings
    -0.73
    govtrack
    -0.73
    WARD
    -0.73
    ulton
    -0.69
    alez
    -0.67
    reek
    -0.67
    aternity
    -0.66
    ospital
    -0.65
    POSITIVE LOGITS
     Chromebook
    1.33
     Pixel
    1.12
     laptops
    0.89
     calcul
    0.83
     Flip
    0.81
     MacBook
    0.78
    Pixel
    0.77
     laptop
    0.76
    aptop
    0.75
     Acer
    0.75
    Activations Density 0.005%

    No Known Activations