INDEX

Explanations

phrases indicating reported speech or explanations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kasarigan

-0.75

chengladbach

-0.57

 GenerationType

-0.54



-0.48

 MutableLiveData

-0.48

blatt

-0.47

"><?

-0.46

Â

-0.44

このような

-0.44

[]{"

-0.43

POSITIVE LOGITS

AnchorStyles

0.92

 réessayer

0.78

Geplaatst

0.75

PerformLayout

0.74

 дописавши

0.68

 kaynağından

0.65

 noting

0.63

ViewFeatures

0.63

abestanden

0.62

RTLR

0.62

Activations Density 0.066%

phrases indicating reported speech or explanations

No Comments

No Known Activations