© 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. 6-RES-JB
    11. 2929
    Prev
    Next
    INDEX
    Explanations

    words related to extreme size or intensity, such as "super" or "huge"

    oai_token-act-pair · gpt-3.5-turbo

    references to "super" in various contexts, often related to significant events or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edIn
    -0.77
     Seym
    -0.75
    Reloaded
    -0.73
     Lauder
    -0.70
    GGGG
    -0.65
     Anger
    -0.63
    66666666
    -0.61
    theless
    -0.61
     Frie
    -0.61
    assetsadobe
    -0.60
    POSITIVE LOGITS
    imposed
    1.36
    nova
    1.18
    visor
    1.15
    charged
    1.13
    cedes
    1.12
    powers
    1.09
    visory
    1.07
    computer
    1.04
    charg
    1.04
    charging
    0.99
    Activations Density 0.019%

    No Known Activations