© 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. 18493
    Prev
    Next
    INDEX
    Explanations

    phrases that prompt the reader to consider different perspectives or framing of concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "think of."

    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
    pite
    -0.70
     promoter
    -0.61
    ollah
    -0.60
    ante
    -0.60
     proclaimed
    -0.59
    Written
    -0.59
     maintained
    -0.59
     differed
    -0.58
    Tweet
    -0.58
    Found
    -0.58
    POSITIVE LOGITS
    èĪ
    0.69
    buck
    0.63
    agine
    0.63
    agus
    0.62
     quitting
    0.61
    abel
    0.61
     è£ıè
    0.61
    agram
    0.61
    gil
    0.60
    swer
    0.60
    Activations Density 0.054%

    No Known Activations