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. 8-RES-JB
    6. 4547
    Prev
    Next
    INDEX
    Explanations

    mentions of software or technical features

    oai_token-act-pair · gpt-3.5-turbo

    instances of support in various contexts, particularly related to technology or applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esta
    -0.78
    sis
    -0.77
    owsky
    -0.75
    eal
    -0.74
    ila
    -0.70
    warm
    -0.70
    arson
    -0.69
    rained
    -0.68
    wage
    -0.68
    asha
    -0.68
    POSITIVE LOGITS
     IPv
    0.81
     HTTPS
    0.73
     Languages
    0.73
     manual
    0.71
     customization
    0.70
    anced
    0.69
     Compatibility
    0.69
     iPhones
    0.69
     JSON
    0.68
     CONFIG
    0.68
    Activations Density 0.085%

    No Known Activations