© 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. 2-RES-JB
    11. 20927
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the initiation of an action or process

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the initiation of events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ighth
    -0.73
    etry
    -0.73
    ugs
    -0.72
    illard
    -0.71
    ethy
    -0.71
    obi
    -0.70
    iliary
    -0.69
    itsch
    -0.68
    angs
    -0.67
    omb
    -0.67
    POSITIVE LOGITS
     anew
    0.94
    starting
    0.83
     PRESS
    0.73
     started
    0.72
     laun
    0.71
    started
    0.70
     raining
    0.70
     airing
    0.69
    OPLE
    0.69
     bothering
    0.68
    Activations Density 0.039%

    No Known Activations