© 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. 17698
    Prev
    Next
    INDEX
    Explanations

    phrases or sequences of characters that may not necessarily form meaningful words

    oai_token-act-pair · gpt-3.5-turbo

    repeated or similar phonetic patterns in words

    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
     optics
    -0.72
    liners
    -0.69
     Emin
    -0.59
     Emmy
    -0.59
     Mysteries
    -0.58
     honesty
    -0.58
     Investigator
    -0.57
     outweigh
    -0.57
     emergencies
    -0.57
     Cosponsors
    -0.56
    POSITIVE LOGITS
    ñ
    1.35
    plin
    1.23
    vern
    1.21
    uthor
    1.19
    ption
    1.16
    ç
    1.14
    vel
    1.13
    BILITY
    1.12
    qual
    1.11
    ï
    1.09
    Activations Density 0.167%

    No Known Activations