© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 7875
    Prev
    Next
    INDEX
    Explanations

    phrases related to headings in a document

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and its variations, indicating a focus on articles and proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ffen
    -0.74
    aea
    -0.74
    olulu
    -0.71
    etsk
    -0.69
    eca
    -0.67
    lets
    -0.65
    nels
    -0.65
    perties
    -0.64
    agate
    -0.64
    cies
    -0.63
    POSITIVE LOGITS
     THE
    1.60
     WEEK
    1.50
     STORY
    1.47
     REPORT
    1.45
     ABOUT
    1.45
     THEIR
    1.44
     PRESIDENT
    1.43
    LINE
    1.43
     THERE
    1.43
    HEAD
    1.43
    Activations Density 0.147%

    No Known Activations