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

    Neuronpedia

    Jacobian LensNEW
    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. 24090
    Prev
    Next
    INDEX
    Explanations

    descriptions related to expansive and established worlds or realms

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to cinematic universes and their development

    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
    arent
    -0.63
     sidx
    -0.61
    oub
    -0.60
    azeera
    -0.58
     prank
    -0.53
     Rab
    -0.53
    aleb
    -0.53
    etooth
    -0.52
    afort
    -0.52
    ideshow
    -0.52
    POSITIVE LOGITS
     trillions
    0.67
     uninterrupted
    0.65
     limitless
    0.64
     billions
    0.61
     habitable
    0.60
     seamlessly
    0.58
     crumbling
    0.58
     encompasses
    0.57
     encomp
    0.57
     thriving
    0.56
    Activations Density 1.292%

    No Known Activations