© 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. 8-RES-JB
    11. 752
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the importance of something or someone

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Without" followed by an emphasis on necessity or lack thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    'without'

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    late
    -0.72
    des
    -0.70
    rolled
    -0.69
     Appears
    -0.68
    mers
    -0.66
    geist
    -0.66
    dry
    -0.66
    umm
    -0.65
    roller
    -0.64
    mun
    -0.62
    POSITIVE LOGITS
     exception
    0.96
     knowing
    0.92
     mentioning
    0.89
     doubt
    0.85
     hesitation
    0.77
     regard
    0.77
     interruption
    0.72
     refriger
    0.71
     adequate
    0.71
     recourse
    0.70
    Activations Density 0.031%

    No Known Activations