© 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. 2-RES-JB
    11. 24180
    Prev
    Next
    INDEX
    Explanations

    words related to legal matters and disputes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "def" and its various forms, indicating a focus on discussions of definitions or legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    externalActionCode
    -0.78
     Archdemon
    -0.76
    ORPG
    -0.67
    DragonMagazine
    -0.66
    worldly
    -0.66
    ppa
    -0.66
    sth
    -0.66
    mares
    -0.65
    544
    -0.65
    jen
    -0.61
    POSITIVE LOGITS
    ibr
    1.04
    ensible
    0.99
    acement
    0.88
    eat
    0.88
    acements
    0.88
    amiliar
    0.87
    anged
    0.86
    inished
    0.86
    erent
    0.85
    luent
    0.84
    Activations Density 0.008%

    No Known Activations