© 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. 11-RES-JB
    11. 11313
    Prev
    Next
    INDEX
    Explanations

    object nouns and related terms, specific to a particular context involving elements like cards, game mechanics, and effects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to spells or magical effects in a gaming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CBS
    -0.81
    Disney
    -0.80
    erences
    -0.78
    NOW
    -0.76
    fecture
    -0.75
    population
    -0.75
    yright
    -0.74
    rito
    -0.74
    isine
    -0.74
    Topics
    -0.73
    POSITIVE LOGITS
     Abyssal
    1.40
     Demonic
    1.32
     Blessing
    1.30
     Primordial
    1.29
     Arcane
    1.28
     Explosive
    1.28
     Plague
    1.23
     Haste
    1.22
     Cursed
    1.22
     Torment
    1.22
    Activations Density 0.181%

    No Known Activations