© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 10692
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal actions and decisions

    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
     newsletters
    -0.66
     Sketch
    -0.65
     hostage
    -0.63
     Future
    -0.59
     Grass
    -0.59
     rename
    -0.57
     nudity
    -0.57
     Reboot
    -0.55
     itch
    -0.55
     underestimate
    -0.55
    POSITIVE LOGITS
     undertaken
    1.09
     achieved
    1.02
     exchanged
    1.01
     devised
    0.97
     given
    0.97
     issued
    0.96
     obtained
    0.95
     taken
    0.93
     enacted
    0.93
     levied
    0.92
    Activations Density 0.163%

    No Known Activations