© 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. 1-RES-JB
    11. 14373
    Prev
    Next
    INDEX
    Explanations

    multi-step processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe a step-by-step process or methodology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ribbon
    -0.70
     persuasive
    -0.69
     peac
    -0.69
     velvet
    -0.68
     fuss
    -0.68
     cush
    -0.68
     disposable
    -0.68
     burnt
    -0.67
     multit
    -0.67
     canned
    -0.67
    POSITIVE LOGITS
    step
    1.32
    DragonMagazine
    1.14
    steps
    0.99
    Step
    0.99
    daughter
    0.89
    STEP
    0.88
    hens
    0.87
    Mania
    0.82
    iblings
    0.81
    dad
    0.81
    Activations Density 0.004%

    No Known Activations