© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7770
    Prev
    Next
    INDEX
    Explanations

    specific steps or instructions

    oai_token-act-pair · gpt-3.5-turbo

    instructional steps in processes or tasks

    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
     favor
    -0.73
     poetry
    -0.69
     favour
    -0.68
     incendiary
    -0.67
     anomal
    -0.67
     omn
    -0.67
     warrant
    -0.66
     poster
    -0.66
     Corpus
    -0.66
     patents
    -0.65
    POSITIVE LOGITS
    Step
    3.76
    step
    2.24
     Step
    2.19
    STEP
    2.18
     Steps
    1.88
     STEP
    1.72
     step
    1.67
    steps
    1.64
     steps
    1.44
     Stephanie
    1.26
    Activations Density 0.018%

    No Known Activations