© 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. 10-RES-JB
    11. 16005
    Prev
    Next
    INDEX
    Explanations

    phrases related to consecutive occurrences or repetition

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "after X," where X represents a numerical value indicating time intervals

    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
    ãĥķãĤ©
    -0.81
    Liquid
    -0.70
     Bows
    -0.68
    Reloaded
    -0.67
     Creatures
    -0.67
     Flavoring
    -0.67
    IPS
    -0.67
    ells
    -0.65
    ATS
    -0.65
     Plays
    -0.64
    POSITIVE LOGITS
     piece
    0.83
     minute
    0.82
     inch
    0.81
     verse
    0.79
     pound
    0.75
     province
    0.75
     week
    0.75
     atroc
    0.75
     toe
    0.75
     symptom
    0.74
    Activations Density 0.046%

    No Known Activations