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. 2-RES-JB
    6. 3000
    Prev
    Next
    INDEX
    Explanations

    information related to fundraising and support requests

    oai_token-act-pair · gpt-3.5-turbo

    elements related to project management and participation details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.90
    deen
    -0.69
     Islamist
    -0.67
    00007
    -0.65
     amput
    -0.64
     Islamists
    -0.63
     himself
    -0.62
     violently
    -0.61
     decap
    -0.61
    bush
    -0.60
    POSITIVE LOGITS
     customizable
    0.88
     customized
    0.85
     customization
    0.83
     format
    0.78
     customize
    0.77
     functionality
    0.77
     personalized
    0.76
     download
    0.75
     Settings
    0.74
     Filter
    0.73
    Activations Density 3.203%

    No Known Activations