© 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. 4-RES-JB
    6. 14280
    Prev
    Next
    INDEX
    Explanations

    comparative expressions related to quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating an increase or decrease in data or statistics

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

    No Comments

    Negative Logits
    Mand
    -0.77
     UNCLASSIFIED
    -0.63
    blogs
    -0.63
    images
    -0.62
    group
    -0.60
     Neon
    -0.60
    media
    -0.60
    WI
    -0.60
    gang
    -0.60
    Ire
    -0.59
    POSITIVE LOGITS
     than
    1.08
    than
    0.81
     Than
    0.79
     bang
    0.70
    ochet
    0.69
    ooters
    0.69
     subsequ
    0.67
     unloaded
    0.67
     equals
    0.66
    ophers
    0.66
    Activations Density 0.090%

    No Known Activations