Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 20475
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computing or electronics, likely related to WM (working memory)

    oai_token-act-pair · gpt-3.5-turbo

    terms related to working memory (WM) and attention measures (WT)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apore
    -0.67
    resso
    -0.65
    mort
    -0.65
     counselors
    -0.64
    otle
    -0.63
     afore
    -0.63
    abad
    -0.63
     Rica
    -0.62
    clinton
    -0.61
    anthrop
    -0.61
    POSITIVE LOGITS
    WM
    1.10
    wm
    0.92
     WM
    0.86
     IPM
    0.86
    idth
    0.79
    è¦ļéĨĴ
    0.78
    FU
    0.77
    ICH
    0.76
    restling
    0.76
    Fs
    0.75
    Activations Density 0.019%

    No Known Activations