© 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 EvalsExportsinterp-engineNEWAPI 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. 18868
    Prev
    Next
    INDEX
    Explanations

    adjectives or nouns related to foundational principles or root causes

    oai_token-act-pair · gpt-3.5-turbo

    references to underlying causes, issues, or factors in various contexts

    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
    aido
    -0.90
    helm
    -0.79
    uba
    -0.77
     Sabha
    -0.76
    udo
    -0.76
    hops
    -0.76
    urate
    -0.75
    asia
    -0.74
    zanne
    -0.73
    hire
    -0.73
    POSITIVE LOGITS
     premise
    1.35
     principle
    1.32
     principles
    1.29
     assumption
    1.24
     rationale
    1.24
     structure
    1.21
     theme
    1.20
     tenets
    1.19
     underlying
    1.18
     motivations
    1.16
    Activations Density 0.082%

    No Known Activations