INDEX

Explanations

terms related to evaluation or assessment, particularly in scientific or medical contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ficulties

-0.51

eabouts

-0.49

 विश्वसनीयता

-0.45

 digitais

-0.45

 recentes

-0.45

))))))))

-0.45

 espr

-0.45

).—

-0.44

 typelib

-0.44

 travaillons

-0.44

POSITIVE LOGITS

glVertex

0.58

/***/

0.57

NewReader

0.54

 vision

0.53

UVWXYZ

0.52

transQ

0.52

ibatis

0.51

mybatisplus

0.50

 TextInputType

0.50

 itinéraires

0.49

Activations Density 1.216%

terms related to evaluation or assessment, particularly in scientific or medical contexts

No Comments

No Known Activations