© 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. 19196
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emphasis or importance

    oai_token-act-pair · gpt-3.5-turbo

    the repeated character 'âĢ' in various contexts

    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
     Peb
    -0.75
    enegger
    -0.73
    anwhile
    -0.70
     scattering
    -0.67
     nearest
    -0.65
     scatter
    -0.63
     dangling
    -0.63
     gad
    -0.62
     lodging
    -0.60
     swept
    -0.59
    POSITIVE LOGITS
    º
    1.31
    £
    1.18
    ¹
    1.17
    ¬
    1.05
    §
    1.03
    į
    1.03
    Į
    1.00
    Ĵ
    1.00
    ¿
    1.00
    ı
    1.00
    Activations Density 0.294%

    No Known Activations