© 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
    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. 10216
    Prev
    Next
    INDEX
    Explanations

    legal and investigative terms related to evidence and actions taken based on evidence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal proceedings and court 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
    dozen
    -0.75
    tiny
    -0.74
    mostly
    -0.74
     wonderfully
    -0.70
    het
    -0.69
     mostly
    -0.69
     famously
    -0.69
    pretty
    -0.68
     beautifully
    -0.68
     brilliantly
    -0.67
    POSITIVE LOGITS
     termination
    1.12
     removal
    1.07
     any
    1.05
     revocation
    1.03
     anything
    1.03
     dismissal
    1.02
     expulsion
    0.96
     imposition
    0.94
    enance
    0.93
     such
    0.93
    Activations Density 0.486%

    No Known Activations