© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 512
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations, people's names, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of places and people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prematurely
    -0.63
    selves
    -0.62
     irresist
    -0.62
    UME
    -0.61
     uneven
    -0.60
     glitches
    -0.60
    rupulous
    -0.60
     manually
    -0.59
     UID
    -0.59
    ebus
    -0.59
    POSITIVE LOGITS
    stown
    1.44
    ville
    1.23
     Creek
    1.08
    sonian
    1.07
     Brothers
    1.06
    sburg
    1.05
    town
    1.04
     Valley
    1.03
     County
    1.02
     Bros
    0.99
    Activations Density 0.230%

    No Known Activations