INDEX

Explanations

references to figures and tables in scientific texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 otherwise

-0.47

 continued

-0.46

olis

-0.46

 poste

-0.44

 ufficiali

-0.44

AddressBook

-0.43

continued

-0.43

twig

-0.43

+#+#

-0.43

ick

-0.43

POSITIVE LOGITS

Figure

0.89

 дописавши

0.85

Рис

0.85

ConstraintMaker

0.82

 Figure

0.77

Fig

0.77

]^{-

0.77

MemoryWarning

0.74

FIG

0.73

FIGURE

0.71

Activations Density 0.126%

references to figures and tables in scientific texts

No Comments

No Known Activations