INDEX

Explanations

references to new developments or changes

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

ῖς

-0.50

BCD

-0.49

reuters

-0.44

reeg

-0.44

σθαι

-0.42

 EINVAL

-0.42

 daž

-0.42

ὺς

-0.42

 epis

-0.42

#+#

-0.41

POSITIVE LOGITS

new

0.93

DockStyle

0.90

 newly

0.87

 kasarigan

0.85

 الجديد

0.83

 nowej

0.83

 nowy

0.82

 revamped

0.81

 nuevo

0.81

 новом

0.81

Activations Density 0.139%

references to new developments or changes

No Comments

No Known Activations