© 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. 2923
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "On the one hand" or similar variations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express contrasting viewpoints or duality in arguments

    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
    hig
    -0.89
    dr
    -0.75
    dra
    -0.74
     VIDEOS
    -0.72
    zag
    -0.69
    sung
    -0.69
    ////////////////
    -0.69
    rawdownloadcloneembedreportprint
    -0.69
    äºĶ
    -0.68
    natureconservancy
    -0.66
    POSITIVE LOGITS
     congratulations
    0.70
     behalf
    0.69
     rejoice
    0.64
     autobi
    0.61
     you
    0.60
     reconcil
    0.59
    aminer
    0.59
     argues
    0.58
     we
    0.57
     representing
    0.56
    Activations Density 0.041%

    No Known Activations