© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19331
    Prev
    Next
    INDEX
    Explanations

    steps or procedures in a series

    oai_token-act-pair · gpt-3.5-turbo

    the concept of sequential processes or instructions

    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
     unaccount
    -0.69
     owned
    -0.62
     anomal
    -0.62
     eas
    -0.62
     monopol
    -0.59
     Mun
    -0.59
     commissioned
    -0.59
     aluminum
    -0.59
     installed
    -0.58
     disl
    -0.58
    POSITIVE LOGITS
    step
    4.47
    steps
    2.77
    STEP
    1.99
     step
    1.97
    Step
    1.95
     Step
    1.92
     STEP
    1.68
    ste
    1.56
     steps
    1.43
     Steps
    1.40
    Activations Density 0.005%

    No Known Activations