© 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. 22898
    Prev
    Next
    INDEX
    Explanations

    terms related to alternating or alternating between different states or activities

    oai_token-act-pair · gpt-3.5-turbo

    patterns of alternation in various contexts

    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
    Delivery
    -0.69
    GER
    -0.69
    abad
    -0.67
    ablishment
    -0.67
    IRO
    -0.66
     Famous
    -0.65
    ASED
    -0.65
    mouth
    -0.65
    GI
    -0.64
    water
    -0.64
    POSITIVE LOGITS
     altern
    1.45
    etheless
    1.04
     alternating
    0.99
     arrang
    0.92
    atility
    0.89
    atile
    0.89
     incorpor
    0.85
     agre
    0.82
     simultane
    0.80
     exha
    0.80
    Activations Density 0.010%

    No Known Activations