© 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. 9-RES-JB
    11. 7092
    Prev
    Next
    INDEX
    Explanations

    descriptions of difficulty or challenge

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating difficulty or challenges in contacting someone or something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     postpone
    -0.74
     exhilar
    -0.71
     overcame
    -0.70
    terness
    -0.69
     rebound
    -0.69
    essim
    -0.69
     rejuven
    -0.68
     plunged
    -0.68
     breakthrough
    -0.67
    anticipated
    -0.67
    POSITIVE LOGITS
     affiliation
    0.96
     disclaim
    0.93
     subsidiaries
    0.91
     legit
    0.87
     google
    0.86
     propriet
    0.85
     reputable
    0.83
     headquartered
    0.82
     advertise
    0.82
     acron
    0.81
    Activations Density 1.223%

    No Known Activations