© 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. 7-RES-JB
    11. 9548
    Prev
    Next
    INDEX
    Explanations

    patterns related to sentence formatting and structure

    oai_token-act-pair · gpt-3.5-turbo

    symbols or special characters and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     satell
    -0.69
     itiner
    -0.67
    ukong
    -0.66
     glim
    -0.66
     brisk
    -0.65
     Byz
    -0.64
     pleasures
    -0.63
     Seym
    -0.61
    icion
    -0.60
     traged
    -0.60
    POSITIVE LOGITS
    %"
    0.88
    TAG
    0.87
    âķIJâķIJ
    0.84
    é¾į
    0.83
    âķIJ
    0.77
    ãĤĮ
    0.77
    âĶĢâĶĢ
    0.74
    âĸĢ
    0.74
    âĸij
    0.74
    λ
    0.73
    Activations Density 0.170%

    No Known Activations