INDEX

Explanations

references to JSON content types and related structures

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

meros

-0.47

sizer

-0.45

 ruota

-0.43

 liên

-0.42

мера

-0.42

windowFixed

-0.42

</strong>

-0.42

ľa

-0.42

kenstock

-0.40

 morreu

-0.40

POSITIVE LOGITS

 चीज़ों

0.80

 autorytatywna

0.77

AddTagHelper

0.76

OGND

0.74

]--;

0.73

abestanden

0.73

NameInMap

0.71

Datuak

0.71

يكب

0.68

AutoField

0.67

Activations Density 0.475%

references to JSON content types and related structures

No Comments

No Known Activations