INDEX

Explanations

items related to clothing or apparel features

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 &___

-0.57

SqlClient

-0.52

enfone

-0.50

geme

-0.49

desa

-0.47

BeginContext

-0.46

 AssemblyTitle

-0.46

yadh

-0.45

 CURIAM

-0.45

niająca

-0.45

POSITIVE LOGITS

 warmth

1.29

 winter

1.21

 shivering

1.18

 warming

1.16

 warm

1.15

 warmest

1.14

 warms

1.11

 Warm

1.10

Winter

1.08

Warm

1.08

Activations Density 0.116%

items related to clothing or apparel features

No Comments

No Known Activations