© 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. 22966
    Prev
    Next
    INDEX
    Explanations

    words associated with steepness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "steep" 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
    ignty
    -0.81
    ufact
    -0.76
    phis
    -0.73
    ubb
    -0.73
     Machina
    -0.72
    gdala
    -0.68
    imester
    -0.67
    aurus
    -0.66
    bers
    -0.65
     Veter
    -0.64
    POSITIVE LOGITS
    ened
    1.05
    ly
    0.99
     slope
    0.96
    ening
    0.96
     slopes
    0.91
    ed
    0.89
    est
    0.86
    fall
    0.81
     gradient
    0.81
    ness
    0.79
    Activations Density 0.034%

    No Known Activations