INDEX

Explanations

data related to locations and specific characteristics within those locations

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

 GenerationType

-0.70

tanleria

-0.66

 <=",

-0.64

 Walkover

-0.63

Hentet

-0.60

 الرياضيه

-0.59

 BorderRadius

-0.58

odotus

-0.58

 ControllerBase

-0.58

#+#

-0.58

POSITIVE LOGITS

 Grunde

0.52

 للتو

0.50

rrggbb

0.50

 public

0.49

rungsseite

0.47

 ویکی‌پدیا

0.47

 Jaffe

0.46

 Wolf

0.44

uidado

0.44

IndentedString

0.43

Activations Density 0.435%

data related to locations and specific characteristics within those locations

No Comments

No Known Activations