INDEX

Explanations

key terms indicating success or victory in competitive 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

IntoConstraints

-1.26

 فريبيس

-1.05

expandindo

-1.03

LookAnd

-1.01

PyExc

-0.97

writeFieldEnd

-0.96

bootstrapcdn

-0.93

 protoimpl

-0.93

 الرياضيه

-0.90

NameInMap

-0.90

POSITIVE LOGITS

haway

0.56

 contrário

0.56

جه

0.55

 interloc

0.51

͐

0.50

 ambiental

0.50

ama

0.49

zuki

0.48

 asma

0.48

 inter

0.47

Activations Density 0.488%

key terms indicating success or victory in competitive contexts

No Comments

No Known Activations