© 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. 12548
    Prev
    Next
    INDEX
    Explanations

    phrases expressing an excessive or overwhelming aspect of a situation or emotion

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "all too" in various contexts

    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
    yout
    -0.73
    layer
    -0.73
    esville
    -0.70
    76561
    -0.69
    agara
    -0.69
    draft
    -0.68
    cius
    -0.66
    oust
    -0.66
    DF
    -0.65
    instein
    -0.65
    POSITIVE LOGITS
     recogn
    0.61
     painfully
    0.61
    entimes
    0.60
     behold
    0.58
     pleased
    0.58
    BuyableInstoreAndOnline
    0.58
     welcome
    0.57
     busy
    0.57
     eager
    0.57
     forget
    0.56
    Activations Density 0.044%

    No Known Activations