© 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. 1816
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific portions or parts of something

    oai_token-act-pair · gpt-3.5-turbo

    references to portions or quantities of items

    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
    omics
    -0.74
    rolog
    -0.65
    arius
    -0.64
     recognised
    -0.62
    uk
    -0.62
    htar
    -0.62
    emi
    -0.61
     ðŁ
    -0.60
    emia
    -0.60
     luck
    -0.57
    POSITIVE LOGITS
     portions
    3.78
     portion
    2.18
     parts
    1.85
     sections
    1.83
     chunks
    1.72
     segments
    1.69
     passages
    1.61
    parts
    1.55
     excerpts
    1.44
     aspects
    1.41
    Activations Density 0.014%

    No Known Activations