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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 1890
    Prev
    Next
    INDEX
    Explanations

    criticisms or shortcomings in various areas such as enforcement, design, data, and services

    oai_token-act-pair · gpt-3.5-turbo

    negative assessments of processes or systems

    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
    ollah
    -0.69
    aceae
    -0.65
    gdala
    -0.63
    sin
    -0.61
    empt
    -0.61
    gone
    -0.59
    ozo
    -0.59
     toast
    -0.58
    oppers
    -0.58
    instein
    -0.58
    POSITIVE LOGITS
     due
    0.89
     academ
    0.89
     miser
    0.84
    due
    0.78
    luster
    0.78
    adequ
    0.76
     compared
    0.76
     owing
    0.72
     adequately
    0.66
     priorities
    0.65
    Activations Density 0.307%

    No Known Activations