© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 2827
    Prev
    Next
    INDEX
    Explanations

    phrases indicating repetition or continuation

    oai_token-act-pair · gpt-3.5-turbo

    repetitive or recurring phrases and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulence
    -0.86
     occurs
    -0.77
    ortmund
    -0.74
    regate
    -0.71
     lasts
    -0.71
     VIDEOS
    -0.70
     arises
    -0.69
    ipeg
    -0.69
     expire
    -0.67
    ggles
    -0.67
    POSITIVE LOGITS
     aware
    1.33
     able
    1.26
     thankful
    1.24
     interested
    1.23
     afraid
    1.22
     obsessed
    1.21
     concerned
    1.18
     ashamed
    1.14
     grateful
    1.14
     trying
    1.14
    Activations Density 0.253%

    No Known Activations