© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 17331
    Prev
    Next
    INDEX
    Explanations

    terms related to marketing and design

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to marketing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inite
    -0.75
    upon
    -0.66
    clud
    -0.65
    deen
    -0.64
    aldo
    -0.62
     captcha
    -0.62
     Resurrection
    -0.61
    SCP
    -0.61
    semble
    -0.61
     Sul
    -0.61
    POSITIVE LOGITS
     campaigns
    1.21
     ploy
    1.02
     campaign
    0.98
     gimm
    0.94
     blitz
    0.93
     strategies
    0.90
     strategy
    0.90
     tactics
    0.89
     stunts
    0.87
    Campaign
    0.87
    Activations Density 0.057%

    No Known Activations