© 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. 8-RES-JB
    11. 17758
    Prev
    Next
    INDEX
    Explanations

    proper nouns or titles of books, movies, albums and TV shows

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the special character "âĢ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shack
    -0.65
     Glou
    -0.63
    anwhile
    -0.61
    hiba
    -0.60
     postal
    -0.60
     divers
    -0.58
    ifications
    -0.58
     scattering
    -0.58
     SUP
    -0.57
     LIN
    -0.57
    POSITIVE LOGITS
    ¬
    1.06
    º
    1.05
    ı
    1.04
    į
    1.04
    Ĵ
    1.01
    ´
    0.98
    ¹
    0.98
    ¡
    0.96
    ľ
    0.96
    »
    0.96
    Activations Density 0.235%

    No Known Activations