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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 7628
    Prev
    Next
    INDEX
    Explanations

    terms related to operating systems, specifically looking for mentions of "OS" along with a specific version number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of operating systems

    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
    ãĥ©ãĥ³
    -0.92
    ãĥ¬
    -0.78
    ãĤ¡
    -0.78
    ered
    -0.76
    ouses
    -0.74
    ries
    -0.72
    staking
    -0.71
    ãĤ©
    -0.70
    ãĥª
    -0.68
    ry
    -0.67
    POSITIVE LOGITS
    OS
    1.07
    ECTION
    0.93
    ystem
    0.91
    DAQ
    0.90
     ANGEL
    0.90
    metics
    0.89
    OME
    0.86
    SI
    0.84
    ITION
    0.83
    ALD
    0.83
    Activations Density 0.009%

    No Known Activations