© 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
    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. 11082
    Prev
    Next
    INDEX
    Explanations

    mentions of private sector or private companies in financial or economic contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the private sector and private insurance

    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
    ange
    -0.78
     Gleaming
    -0.75
    older
    -0.72
    EFF
    -0.69
    azi
    -0.69
    itives
    -0.68
    tto
    -0.68
     Luffy
    -0.68
    Days
    -0.66
     Frie
    -0.65
    POSITIVE LOGITS
     sector
    1.48
    sector
    1.20
     enterprises
    1.20
     sectors
    1.14
     entities
    1.11
     insurers
    1.11
     enterprise
    1.10
     corporations
    1.09
     subsidized
    1.06
     firms
    1.06
    Activations Density 0.094%

    No Known Activations