© 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. 9-RES-JB
    11. 7516
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantities or proportions

    oai_token-act-pair · gpt-3.5-turbo

    references to proportions or ratios in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sands
    -0.64
     Brunswick
    -0.64
    RAW
    -0.60
    åĤ
    -0.58
     disclaim
    -0.57
     Trop
    -0.56
     Surviv
    -0.55
     Despair
    -0.55
    DIT
    -0.54
    Cond
    -0.54
    POSITIVE LOGITS
     thereof
    1.08
     fraction
    0.85
    ate
    0.84
    ths
    0.80
    ately
    0.77
    atical
    0.76
     (<
    0.76
    rary
    0.71
    imet
    0.71
    ority
    0.71
    Activations Density 0.044%

    No Known Activations