© 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. 11-RES-JB
    11. 7800
    Prev
    Next
    INDEX
    Explanations

    phrases related to offering support or resources

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "putting up" something, often in a numerical or supportive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administ
    -0.67
    GEN
    -0.62
    involved
    -0.61
    enfranch
    -0.60
    "]=>
    -0.59
    iency
    -0.58
     Aware
    -0.57
    ï¸ı
    -0.57
     Sample
    -0.57
    =[
    -0.56
    POSITIVE LOGITS
     billboards
    0.88
     posters
    0.87
     flyers
    0.85
     barriers
    0.82
     bids
    0.80
     defences
    0.80
     obstacles
    0.76
     defenses
    0.74
     hurdles
    0.73
     banners
    0.73
    Activations Density 0.101%

    No Known Activations