© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 2049
    Prev
    Next
    INDEX
    Explanations

    general adjectives describing quantity or size

    oai_token-act-pair · gpt-3.5-turbo

    terms relating to size or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    events
    -0.93
    iddles
    -0.91
    speak
    -0.90
    hops
    -0.85
    tags
    -0.83
    aunts
    -0.82
    hots
    -0.81
    ults
    -0.79
     Releases
    -0.78
    Frames
    -0.78
    POSITIVE LOGITS
     amount
    1.23
     swath
    1.11
     degree
    1.08
     number
    1.04
     subset
    1.00
     percentage
    0.98
     chunk
    0.97
     variety
    0.95
     portion
    0.95
     range
    0.93
    Activations Density 0.196%

    No Known Activations