© 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. 7-RES-JB
    6. 15236
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology updates and releases

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns indicating ownership or association with entities

    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
    nin
    -0.83
    lehem
    -0.80
    hari
    -0.76
    orgetown
    -0.74
    Filename
    -0.74
    olkien
    -0.71
    ersed
    -0.70
    Assad
    -0.67
    tale
    -0.67
    nington
    -0.66
    POSITIVE LOGITS
     own
    1.45
     flagship
    1.16
     proprietary
    1.09
     customers
    1.05
     competitors
    1.02
     products
    1.02
     newest
    1.01
     subsidiaries
    1.00
     patented
    0.97
     predecessor
    0.95
    Activations Density 0.254%

    No Known Activations