INDEX

Explanations

italicized phrases related to procedures or instructions

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

Spoljašnje

-0.55

znego

-0.53

 shut

-0.50

uglify

-0.47

 franceses

-0.47

unittest

-0.46

Identyfik

-0.46

 tillegg

-0.46

 ferdig

-0.46

 australiano

-0.45

POSITIVE LOGITS

 صوتيه

0.93

homonymie

0.80

 متعلقه

0.71

 gynhyrchwyd

0.68

icitis

0.67

المكان

0.67

 BIND

0.64

 actionMode

0.63

LayoutConstraint

0.60

uities

0.58

Activations Density 1.145%

italicized phrases related to procedures or instructions

No Comments

No Known Activations