© 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. 1254
    Prev
    Next
    INDEX
    Explanations

    phrases indicating incapability or impossibility

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the word "be" 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
    phabet
    -0.77
    rones
    -0.72
     Need
    -0.70
     Newspaper
    -0.67
    OUS
    -0.67
     Tablet
    -0.65
     Lauder
    -0.65
     fray
    -0.64
    plates
    -0.63
    ele
    -0.62
    POSITIVE LOGITS
     construed
    1.23
     traced
    1.20
     trusted
    1.12
     undone
    1.09
     interpreted
    1.08
     blamed
    1.07
     reconcil
    1.06
     avoided
    1.03
     attributed
    1.03
     summed
    1.01
    Activations Density 0.063%

    No Known Activations