© 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. 2943
    Prev
    Next
    INDEX
    Explanations

    words related to proof and evidence

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts related to proof and validation

    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
    soever
    -0.86
     toget
    -0.74
     ILCS
    -0.72
    sembly
    -0.71
    --+
    -0.70
    yip
    -0.69
     Shutterstock
    -0.69
    Interstitial
    -0.65
    backs
    -0.64
    loads
    -0.64
    POSITIVE LOGITS
     existence
    1.77
     validity
    1.70
     authenticity
    1.60
     innocence
    1.50
     legitimacy
    1.44
     correctness
    1.35
     superiority
    1.28
     accuracy
    1.25
     sincerity
    1.24
     efficacy
    1.22
    Activations Density 0.222%

    No Known Activations