© 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. 0-RES-JB
    11. 6801
    Prev
    Next
    INDEX
    Explanations

    terms related to legal matters, contracts, and law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to agents and agencies, particularly in a legal or sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prol
    -0.76
     Rush
    -0.74
     snowy
    -0.67
     breeze
    -0.67
     contin
    -0.66
     discontin
    -0.66
     elevation
    -0.65
     flush
    -0.64
     Rhode
    -0.64
     Pope
    -0.63
    POSITIVE LOGITS
    agent
    4.27
    agents
    3.36
    Agent
    2.16
    agency
    1.73
    uid
    1.08
    trap
    1.00
    gerald
    0.95
    tools
    0.93
    reader
    0.91
    bugs
    0.90
    Activations Density 0.025%

    No Known Activations