© 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. 10698
    Prev
    Next
    INDEX
    Explanations

    adjectives describing the characteristics of things or entities

    oai_token-act-pair · gpt-3.5-turbo

    sentences affirming the existence or status of subjects

    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
    oice
    -0.71
     wipes
    -0.68
    Laughs
    -0.67
    Leave
    -0.66
     congr
    -0.66
    Fix
    -0.65
     Nope
    -0.65
    Yeah
    -0.64
    laughs
    -0.63
    stop
    -0.62
    POSITIVE LOGITS
     characterized
    1.31
     regarded
    1.25
     commonly
    1.22
     distinguished
    1.19
     contrasted
    1.17
     therefore
    1.15
     considered
    1.13
     often
    1.12
     depicted
    1.12
     usually
    1.11
    Activations Density 0.315%

    No Known Activations