© 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. 11-RES-JB
    11. 22463
    Prev
    Next
    INDEX
    Explanations

    components of chemical reactions or scientific processes

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly Harry Reid, and actions related to chemical reactions

    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
    teenth
    -0.74
    ciating
    -0.67
    cas
    -0.63
    holders
    -0.63
    tered
    -0.60
     deduction
    -0.59
     behav
    -0.59
     anecd
    -0.58
    DragonMagazine
    -0.58
     pastoral
    -0.58
    POSITIVE LOGITS
    ors
    0.86
    ivated
    0.84
    nor
    0.83
    ivation
    0.81
    anche
    0.78
    ãĤ©
    0.78
    ishi
    0.76
    ifying
    0.76
    actor
    0.76
    INGTON
    0.75
    Activations Density 0.125%

    No Known Activations