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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 14898
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software, computer systems, and cybersecurity

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to technology and information systems, particularly focused on Windows-based environments and security

    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
    arak
    -0.81
    ĸļ
    -0.75
    hetti
    -0.71
    hur
    -0.71
    ranged
    -0.68
    hm
    -0.67
    ricks
    -0.67
    ðĿ
    -0.67
    verett
    -0.66
    itsch
    -0.65
    POSITIVE LOGITS
     PowerShell
    0.91
     Linux
    0.89
     filesystem
    0.89
    agate
    0.88
     authentication
    0.88
     daemon
    0.85
     Authentication
    0.84
     malware
    0.83
     Server
    0.83
     login
    0.83
    Activations Density 0.509%

    No Known Activations