© 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. 7221
    Prev
    Next
    INDEX
    Explanations

    the word "Em" or variations of it in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the abbreviation "Em" likely referring to a notable name or entity

    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
     Kubrick
    -0.81
    aird
    -0.75
    WAYS
    -0.71
     sund
    -0.69
     ASC
    -0.68
    ãģį
    -0.68
     Icelandic
    -0.68
     Manitoba
    -0.66
     Saskatchewan
    -0.66
    Lago
    -0.65
    POSITIVE LOGITS
    phasis
    1.31
    otions
    1.24
    otional
    1.21
    igrant
    1.19
    phas
    1.15
    igrants
    1.14
    otion
    1.14
    ission
    1.14
    brace
    1.10
    blems
    1.08
    Activations Density 0.005%

    No Known Activations