Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 17187
    Prev
    Next
    INDEX
    Explanations

    legal terms and actions related to temporary matters

    oai_token-act-pair · gpt-3.5-turbo

    references to temporary legal or regulatory measures

    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
    fman
    -0.86
    riad
    -0.82
     DRAG
    -0.75
    20439
    -0.75
    gerald
    -0.74
    bold
    -0.74
    iosyncr
    -0.74
    artz
    -0.74
    gans
    -0.73
    icist
    -0.73
    POSITIVE LOGITS
     restraining
    1.30
     lodging
    0.98
     halt
    0.97
     accommodation
    0.97
     truce
    0.95
     suspension
    0.94
     moratorium
    0.94
     refuge
    0.92
     halting
    0.91
     injunction
    0.90
    Activations Density 0.052%

    No Known Activations