© 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. 20512
    Prev
    Next
    INDEX
    Explanations

    references to research studies and reports

    oai_token-act-pair · gpt-3.5-turbo

    references to academic studies and research papers

    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
    OPA
    -0.66
     dying
    -0.64
    âĹ¼
    -0.64
    cius
    -0.63
    animate
    -0.63
    onz
    -0.63
    vp
    -0.63
     riot
    -0.59
    ventus
    -0.59
     whispering
    -0.58
    POSITIVE LOGITS
     focuses
    1.39
     emphasizes
    1.28
     highlights
    1.27
     includes
    1.26
     examines
    1.26
     demonstrates
    1.24
     underscores
    1.23
     provides
    1.22
     illustrates
    1.22
     explores
    1.21
    Activations Density 0.181%

    No Known Activations