© 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. 9-RES-JB
    6. 6932
    Prev
    Next
    INDEX
    Explanations

    entities or locations followed by the word "be"

    oai_token-act-pair · gpt-3.5-turbo

    the verb "be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azines
    -0.75
    rador
    -0.72
    antha
    -0.70
    pick
    -0.68
    pai
    -0.67
    phis
    -0.66
     Ples
    -0.65
    laus
    -0.63
     Relief
    -0.62
     Bundy
    -0.61
    POSITIVE LOGITS
    yond
    1.57
    FORE
    1.26
    arers
    1.07
    arer
    1.06
    cker
    1.03
    gotten
    0.99
    ijing
    0.97
    hold
    0.89
    asts
    0.88
    AUT
    0.88
    Activations Density 0.050%

    No Known Activations