INDEX

Explanations

words and phrases that indicate structure or organization in documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

niv

-0.55

—

-0.55

feu

-0.54

otone

-0.54

OrEqualTo

-0.50

…

-0.49

xiu

-0.47

 stunning

-0.46

ख्य

-0.46

jillo

-0.45

POSITIVE LOGITS

<bos>

2.29

LookAnd

1.07

 kaarangay

0.97

 виправивши

0.96

 дописавши

0.95

 Савезне

0.95

abestanden

0.92

 nakalista

0.85

 Numerade

0.82

 Мексичка

0.79

Activations Density 0.801%

words and phrases that indicate structure or organization in documentation

No Comments

No Known Activations