© 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. 6-RES-JB
    11. 1564
    Prev
    Next
    INDEX
    Explanations

    numerical values related to measurements such as square footage, seat capacity, and voltage

    oai_token-act-pair · gpt-3.5-turbo

    negative values related to sizes or dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cassidy
    -0.72
     Rica
    -0.71
     Defenders
    -0.67
     Scrib
    -0.67
     Browne
    -0.66
     solicitation
    -0.65
     Cyrus
    -0.64
     Creator
    -0.64
     Aval
    -0.63
     Randolph
    -0.63
    POSITIVE LOGITS
    degree
    1.14
    million
    1.13
    percent
    1.13
    plus
    1.10
    caliber
    1.09
    pound
    1.06
    year
    1.05
    dollar
    1.03
    sized
    1.02
    based
    1.00
    Activations Density 0.065%

    No Known Activations