INDEX

Explanations

the word "which" and its grammatical forms in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 EconPapers

-0.82

WithIOException

-0.80

 insuffisamment

-0.79

 كومونز

-0.79

 intptr

-0.75

expandindo

-0.72

DoubleQuotes

-0.72

BeginContext

-0.70

########.

-0.69

AndEndTag

-0.69

POSITIVE LOGITS

 antaranya

0.74

 которой

0.56

 которого

0.56

hich

0.48

 zaś

0.47

 cuales

0.47

 which

0.46

 которых

0.46

 якого

0.45

 duquel

0.44

Activations Density 0.232%

the word "which" and its grammatical forms in various contexts

No Comments

No Known Activations