© 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. 11-RES-JB
    11. 1840
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial matters

    oai_token-act-pair · gpt-3.5-turbo

    punctuated statements, particularly those that end with a period

    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
     tremend
    -1.06
     thous
    -1.05
     advoc
    -1.01
     satell
    -0.95
     destro
    -0.92
     corrid
    -0.92
     gobl
    -0.91
     tyr
    -0.90
     entreprene
    -0.90
    ¥ŀ
    -0.90
    POSITIVE LOGITS
     Fortunately
    1.24
     Thankfully
    1.24
     Nonetheless
    1.21
     Luckily
    1.20
    <|endoftext|>
    1.20
     Which
    1.19
     Meanwhile
    1.19
     Needless
    1.18
     Indeed
    1.18
     Presumably
    1.17
    Activations Density 0.604%

    No Known Activations