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. 1-RES-JB
    6. 7780
    Prev
    Next
    INDEX
    Explanations

    terms related to cumulative data or figures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cumulative measurements and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yer
    -0.84
    hod
    -0.77
    orters
    -0.74
    ournal
    -0.74
    ket
    -0.73
    inance
    -0.72
    glers
    -0.72
    neys
    -0.72
    kers
    -0.71
    yers
    -0.70
    POSITIVE LOGITS
     cumulative
    1.20
    ulative
    1.15
     additive
    0.91
     Pengu
    0.90
     dose
    0.76
     shenan
    0.76
    intendent
    0.74
     exposures
    0.74
    enza
    0.74
     unbeliev
    0.73
    Activations Density 0.006%

    No Known Activations