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

    Neuronpedia

    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. 2-RES-JB
    11. 17277
    Prev
    Next
    INDEX
    Explanations

    mentions of programs or initiatives labeled as "scheme"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "scheme" in various contexts

    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
    cknowled
    -0.67
    minent
    -0.60
    jiang
    -0.59
    Nob
    -0.59
     Hug
    -0.58
     resurg
    -0.56
    ãģĹ
    -0.56
     separatist
    -0.56
     Argentine
    -0.56
     humble
    -0.56
    POSITIVE LOGITS
     scheme
    1.27
     schemes
    1.24
     Scheme
    0.96
    ĸļ
    0.80
    ulence
    0.79
    olester
    0.77
    escape
    0.77
    matically
    0.77
     devised
    0.76
    ality
    0.75
    Activations Density 0.008%

    No Known Activations