© 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. 10-RES-JB
    11. 23420
    Prev
    Next
    INDEX
    Explanations

    phrases related to starting or initiating something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "begin."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    allo
    -0.72
    ndra
    -0.67
    ppo
    -0.65
    eros
    -0.64
    aths
    -0.62
    outed
    -0.62
    aky
    -0.62
     backs
    -0.60
    dad
    -0.60
    yip
    -0.60
    POSITIVE LOGITS
     anew
    1.21
    nings
    0.78
    ŃĶ
    0.72
     circulating
    0.71
     preparations
    0.69
     CPR
    0.69
     transitioning
    0.67
    ners
    0.66
     trending
    0.66
    prise
    0.66
    Activations Density 0.052%

    No Known Activations