© 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. 10-RES-JB
    11. 18565
    Prev
    Next
    INDEX
    Explanations

    specific combinations of letters with varied meanings

    oai_token-act-pair · gpt-3.5-turbo

    capital letters and acronyms that likely refer to organizations or specific entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     altogether
    -0.78
     pleas
    -0.68
     stat
    -0.65
     arbitrarily
    -0.64
     leftover
    -0.64
     given
    -0.64
     lowly
    -0.63
     describ
    -0.62
     proverb
    -0.62
    ÙIJ
    -0.62
    POSITIVE LOGITS
    uctions
    1.21
    eworks
    1.18
    istries
    1.15
    ifles
    1.14
    astery
    1.12
    Ħ¢
    1.10
    nr
    1.09
    ifts
    1.03
    ounces
    1.00
    ernels
    0.95
    Activations Density 0.224%

    No Known Activations