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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 11491
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific political, economic, social, and technological topics

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" used in various contexts

    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
    Background
    -0.74
    perse
    -0.70
    rade
    -0.68
    ¶
    -0.68
    ndum
    -0.64
    tel
    -0.62
    ccoli
    -0.62
    âĢł
    -0.61
    abin
    -0.61
    adeon
    -0.61
    POSITIVE LOGITS
     latter
    1.37
    oret
    1.37
     equivalent
    1.21
     hallmark
    1.15
     ones
    1.15
     longest
    1.13
     kind
    1.11
     same
    1.10
     implication
    1.07
     sort
    1.05
    Activations Density 0.176%

    No Known Activations