© 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. 0-RES-JB
    11. 7723
    Prev
    Next
    INDEX
    Explanations

    steps or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to "step," indicating progression or actions taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Corpus
    -0.72
    Wars
    -0.70
    casters
    -0.69
    urban
    -0.66
    76561
    -0.64
    lib
    -0.63
     Admir
    -0.62
     Unlimited
    -0.62
    Magazine
    -0.61
    icle
    -0.61
    POSITIVE LOGITS
     step
    3.83
    step
    2.56
     steps
    2.40
     Step
    2.39
    Step
    1.93
     Steps
    1.87
     STEP
    1.86
    steps
    1.78
     stepping
    1.66
     stride
    1.63
    Activations Density 0.014%

    No Known Activations