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. 10-RES-JB
    6. 23778
    Prev
    Next
    INDEX
    Explanations

    terms related to enterprise cloud services and solutions, particularly focusing on Microsoft Azure

    oai_token-act-pair · gpt-3.5-turbo

    terms related to enterprise technology and cloud computing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.84
    oria
    -0.83
    orie
    -0.79
    igel
    -0.78
    orical
    -0.76
    itsch
    -0.75
    oric
    -0.70
     graffiti
    -0.70
    abet
    -0.70
    tered
    -0.69
    POSITIVE LOGITS
     deployments
    1.26
     Linux
    1.12
     Server
    1.08
     deployment
    1.08
     Deploy
    1.06
     firewall
    1.06
     IoT
    1.04
    Deploy
    1.04
     computing
    1.04
     appliance
    1.03
    Activations Density 0.160%

    No Known Activations