© 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. 4-RES-JB
    6. 12025
    Prev
    Next
    INDEX
    Explanations

    specific named entities, such as locations, people, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals, locations, and specific events

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

    No Comments

    Negative Logits
    ĵĺ
    -0.62
     Brist
    -0.48
     AMA
    -0.47
     âĢº
    -0.47
     Adren
    -0.47
     Ag
    -0.47
     Thanksgiving
    -0.46
    mx
    -0.45
     Cul
    -0.43
     Zac
    -0.43
    POSITIVE LOGITS
    miah
    0.57
    eport
    0.57
    idon
    0.57
    ichick
    0.54
    gins
    0.53
    umbledore
    0.52
    ebted
    0.51
    imore
    0.51
    illet
    0.50
    veland
    0.50
    Activations Density 2.495%

    No Known Activations