INDEX

Explanations

technical details and data presentation in scientific 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

раздо

-0.52

 stället

-0.47

 utafitiHapana

-0.46

specialchars

-0.45

########.

-0.44

 σχέ

-0.43

ulsive

-0.43

fjspx

-0.42

⎩

-0.42

ACTUAL

-0.42

POSITIVE LOGITS

 nearby

0.85

 تضيفلها

0.65

enumi

0.63

 adjacent

0.61

basicConfig

0.61

ContentAlignment

0.60

+#+#

0.60

zeera

0.58

UMBIA

0.58

 yonder

0.57

Activations Density 0.489%

technical details and data presentation in scientific contexts

No Comments

No Known Activations