© 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. 23791
    Prev
    Next
    INDEX
    Explanations

    references to specific entities, such as buildings, products, or literary works

    oai_token-act-pair · gpt-3.5-turbo

    instances and descriptions of significant entities or objects

    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
    respons
    -0.79
    apses
    -0.78
    aws
    -0.76
    opian
    -0.76
    apes
    -0.75
    itudes
    -0.75
    aneers
    -0.74
    agi
    -0.74
    hours
    -0.74
    Ĭ±
    -0.74
    POSITIVE LOGITS
     venerable
    1.01
     guy
    0.99
     sucker
    0.99
     masterpiece
    0.95
     installment
    0.92
     magnificent
    0.92
     amazing
    0.90
     iteration
    0.90
     delightful
    0.89
     mammoth
    0.89
    Activations Density 0.204%

    No Known Activations