INDEX

Explanations

the word "that" 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 @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

<bos>

-0.51

hdys

-0.50

 deber

-0.50

Table

-0.47

ธี

-0.46

ষ্

-0.45

 ско

-0.45

îi

-0.44

 presenza

-0.44

 artikkeli

-0.44

POSITIVE LOGITS

tvguidetime

0.98

 виправивши

0.91

 same

0.86

ſelf

0.83

yntaxException

0.82

 Biôgrafia

0.80

 ويكيميديا

0.78

bewerken

0.77

BagLayout

0.76

ArrowToggle

0.75

Activations Density 0.105%

the word "that" in various contexts

No Comments

No Known Activations