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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 8613
    Prev
    Next
    INDEX
    Explanations

    references to news outlets or publications

    oai_token-act-pair · gpt-3.5-turbo

    specific newspaper names and references to news outlets

    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
     enroll
    -0.66
    avorite
    -0.64
    gone
    -0.61
    ascript
    -0.60
     wrists
    -0.59
     footsteps
    -0.58
     enrolled
    -0.58
     Canaveral
    -0.58
    uddenly
    -0.57
    utations
    -0.55
    POSITIVE LOGITS
     Observer
    0.75
     Blog
    0.75
     Tribune
    0.74
     Inquiry
    0.74
     Gazette
    0.71
    Desk
    0.71
    atmeal
    0.71
     Encyclopedia
    0.71
    Journal
    0.71
     Shed
    0.69
    Activations Density 0.098%

    No Known Activations