© 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. 20605
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant or prominent things/events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "big" or its variations

    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
    Dialogue
    -0.76
    ILA
    -0.75
    Ô
    -0.69
    theless
    -0.68
    rentice
    -0.66
    displayText
    -0.66
    DragonMagazine
    -0.66
    ICLE
    -0.66
    heit
    -0.64
    THER
    -0.64
    POSITIVE LOGITS
    gest
    1.21
     picture
    1.08
    oted
    0.98
    gie
    0.96
     daddy
    0.94
     takeaway
    0.92
     bang
    0.90
    ots
    0.89
    wig
    0.87
     elephant
    0.87
    Activations Density 0.049%

    No Known Activations