© 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. 2-RES-JB
    6. 8059
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Word" in various contexts, potentially focusing on software specific to Word processing

    oai_token-act-pair · gpt-3.5-turbo

    references to the word processing software "Word" and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \/\/
    -0.79
    Interstitial
    -0.77
    olson
    -0.76
     unnecess
    -0.76
    ORK
    -0.72
    âĸ
    -0.72
    etheus
    -0.71
    asio
    -0.71
    ocal
    -0.70
    LECT
    -0.69
    POSITIVE LOGITS
     Word
    1.21
    sworth
    1.16
    press
    1.12
    Word
    1.08
    Press
    0.88
    Pad
    0.84
    lins
    0.79
    word
    0.78
     Trafford
    0.74
    Perfect
    0.74
    Activations Density 0.005%

    No Known Activations