© 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. 17352
    Prev
    Next
    INDEX
    Explanations

    phrases indicating dedication or commitment to a particular cause or activity

    oai_token-act-pair · gpt-3.5-turbo

    expressions of commitment and dedication to a cause or activity

    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
    COL
    -0.63
    estamp
    -0.63
    corn
    -0.62
    inn
    -0.61
    NING
    -0.60
    WARN
    -0.60
    天
    -0.59
    itta
    -0.59
    ©
    -0.59
    ared
    -0.58
    POSITIVE LOGITS
     devoted
    0.88
     solely
    0.79
    ciating
    0.79
     dedicated
    0.79
     dedicate
    0.75
     IPM
    0.74
     exclusively
    0.72
    itures
    0.72
    yles
    0.70
     plaque
    0.68
    Activations Density 0.034%

    No Known Activations