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. 9-RES-JB
    6. 12394
    Prev
    Next
    INDEX
    Explanations

    mentions of names or titles starting with "Mil" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Mil" or similar variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     depreciation
    -0.76
    OPLE
    -0.72
    LY
    -0.71
     compr
    -0.71
    ORTS
    -0.69
     Sorceress
    -0.66
    BOOK
    -0.65
    Ħ¢
    -0.65
     Atlantis
    -0.64
    IELD
    -0.64
    POSITIVE LOGITS
    estones
    1.37
    estone
    1.32
    ksh
    1.29
    waukee
    1.25
    gram
    1.16
    isec
    1.15
    ieu
    1.13
    itant
    1.08
    itar
    1.06
    itary
    1.03
    Activations Density 0.029%

    No Known Activations