© 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. 0-RES-JB
    11. 11367
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal clients

    oai_token-act-pair · gpt-3.5-turbo

    references to clients or customer relationships in various contexts

    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
    umber
    -0.69
    iral
    -0.67
    frac
    -0.65
    malink
    -0.64
    rab
    -0.64
     Haram
    -0.63
    icol
    -0.63
    icist
    -0.62
    chance
    -0.61
    olon
    -0.59
    POSITIVE LOGITS
     clients
    3.99
     client
    2.84
     customers
    1.99
     Client
    1.93
    client
    1.91
    Client
    1.76
     Customers
    1.56
     patients
    1.48
     guests
    1.43
     peers
    1.40
    Activations Density 0.007%

    No Known Activations