© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 19604
    Prev
    Next
    INDEX
    Explanations

    phrases related to information technology and infrastructure, such as cloud deployments, virtual machines, and security solutions

    oai_token-act-pair · gpt-3.5-turbo

    technical terminology related to cloud computing and infrastructure

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

    No Comments

    Negative Logits
    itsch
    -0.96
    oria
    -0.87
    sonian
    -0.87
    orical
    -0.80
    orie
    -0.78
    oric
    -0.76
    rahim
    -0.75
    hemy
    -0.73
    TextColor
    -0.73
    rouse
    -0.72
    POSITIVE LOGITS
     appliance
    1.02
     Linux
    0.98
     controller
    0.97
     deployments
    0.96
     operating
    0.93
    Deploy
    0.93
     configurations
    0.92
     configuration
    0.91
     computing
    0.90
     server
    0.90
    Activations Density 0.173%

    No Known Activations