© 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. 2-RES-JB
    11. 17606
    Prev
    Next
    INDEX
    Explanations

    phrases related to memories or historical events

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to narratives and storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rab
    -0.66
    rella
    -0.61
    Beg
    -0.61
    Topics
    -0.60
    inton
    -0.58
    Lot
    -0.58
     decency
    -0.57
    oway
    -0.57
    zee
    -0.56
     Isle
    -0.56
    POSITIVE LOGITS
    ynthesis
    1.10
    ories
    1.09
    poons
    1.07
    mith
    0.90
    hops
    0.88
    peak
    0.86
    ynt
    0.85
    uggest
    0.85
    pring
    0.83
    ystem
    0.79
    Activations Density 0.009%

    No Known Activations