Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 18334
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "us"

    oai_token-act-pair · gpt-3.5-turbo

    references to assistance and direction in a context involving authority figures or organizations

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

    No Comments

    Negative Logits
    oard
    -0.79
    prison
    -0.76
    rals
    -0.70
    aband
    -0.69
    sec
    -0.67
    col
    -0.67
    ipolar
    -0.67
    celer
    -0.66
    reen
    -0.66
    readable
    -0.65
    POSITIVE LOGITS
    ï¸ı
    0.78
     AMA
    0.65
     ACPI
    0.61
     WIN
    0.61
    ournals
    0.61
     Mig
    0.60
     Grow
    0.59
    è¯
    0.59
     wart
    0.59
     mars
    0.58
    Activations Density 0.000%

    No Known Activations