© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 11226
    Prev
    Next
    INDEX
    Explanations

    references to the term "Tw" followed by a number ranging from 8 to 10

    oai_token-act-pair · gpt-3.5-turbo

    references to Twitter and related platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    senal
    -0.76
    ãĤŃ
    -0.72
    ãģĤ
    -0.71
     territorial
    -0.71
    ulative
    -0.68
     PRESS
    -0.67
    vasive
    -0.66
     living
    -0.64
     confined
    -0.63
    ++++++++++++++++
    -0.63
    POSITIVE LOGITS
    orks
    1.06
    ipes
    1.05
    elfth
    1.05
    icket
    0.99
    ares
    0.99
    urst
    0.98
    eenth
    0.97
    eries
    0.95
    itters
    0.94
    igg
    0.93
    Activations Density 0.006%

    No Known Activations