© 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. 23598
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that highlight the significance or importance of a subject

    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
    idth
    -0.70
    berra
    -0.64
     hello
    -0.62
     Bradley
    -0.61
     Carlton
    -0.60
     Seah
    -0.60
     hoop
    -0.59
    ruction
    -0.58
    inav
    -0.58
     hoops
    -0.57
    POSITIVE LOGITS
     unsu
    1.03
     unus
    0.96
     susceptible
    0.89
     uniquely
    0.88
     unlikely
    0.88
     ineligible
    0.85
     unfit
    0.82
     eligible
    0.80
     liable
    0.80
     safer
    0.77
    Activations Density 0.096%

    No Known Activations