© 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. 6107
    Prev
    Next
    INDEX
    Explanations

    expressions related to efforts or attempts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "get" in various contexts

    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
     Archdemon
    -0.64
     Britann
    -0.63
     Duty
    -0.63
     Sie
    -0.61
    iege
    -0.60
     annex
    -0.59
     depiction
    -0.58
    cair
    -0.58
    mare
    -0.57
     Wonders
    -0.57
    POSITIVE LOGITS
     rid
    1.29
    TING
    0.87
     acquainted
    0.84
    tin
    0.79
    ãĥ³ãĤ¸
    0.79
    away
    0.79
     away
    0.75
    aways
    0.74
     distracted
    0.72
     bog
    0.72
    Activations Density 0.103%

    No Known Activations