© 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. 9406
    Prev
    Next
    INDEX
    Explanations

    size-related descriptions and comparisons

    oai_token-act-pair · gpt-3.5-turbo

    descriptive adjectives indicating size or quality

    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
    CLASSIFIED
    -0.81
    ibrary
    -0.81
    CHAT
    -0.75
    Sense
    -0.68
    BUT
    -0.67
    DB
    -0.67
    Beat
    -0.66
    Helper
    -0.65
    atorium
    -0.65
    tops
    -0.64
    POSITIVE LOGITS
     distances
    0.77
     faults
    0.76
     agric
    0.71
    ifiable
    0.69
    iated
    0.69
     bends
    0.68
    interstitial
    0.66
     exert
    0.64
     neighbours
    0.64
     tempt
    0.64
    Activations Density 0.109%

    No Known Activations