INDEX

Explanations

the word "the" across various contexts in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-1.52

 Theſe

-1.39

 itſelf

-1.39

 Monfieur

-1.35

 ſeveral

-1.34

 myſelf

-1.32

 iſt

-1.31

 whoſe

-1.31

 himſelf

-1.30

 étoient

-1.30

POSITIVE LOGITS

of

1.36

du

0.86

0.79

del

0.79

des

0.78

0.77

of

0.77

↵↵

0.73

0.72

Activations Density 0.629%

the word "the" across various contexts in the text

No Comments

No Known Activations