© 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. 8-RES-JB
    11. 22391
    Prev
    Next
    INDEX
    Explanations

    words related to scope or scale, looking for terms that refer to a broader or wider context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to comparisons to larger groups or contexts

    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
    girls
    -0.83
    visor
    -0.81
    visors
    -0.76
    orneys
    -0.75
    girl
    -0.75
    eva
    -0.74
    Guard
    -0.72
    itors
    -0.72
    ird
    -0.71
     Drawn
    -0.70
    POSITIVE LOGITS
     societal
    1.10
     context
    0.94
     organis
    0.90
     cultural
    0.88
     systemic
    0.87
     implications
    0.84
     ecosystem
    0.84
     spectrum
    0.84
     circulation
    0.84
     socio
    0.84
    Activations Density 0.054%

    No Known Activations