INDEX

Explanations

superlative adjectives and phrases indicating extremes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.hook_mlp_out

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

 most

-1.60

Most

-1.34

 Most

-1.28

most

-1.23

 MOST

-1.05

 meisten

-0.93

大多数

-0.88

 kebanyakan

-0.87

 большинство

-0.86

大部分

-0.84

POSITIVE LOGITS

zzleHttp

0.84

sizeCache

0.83

OGND

0.79

 مشين

0.78

جوايز

0.78

AddHtmlAttribute

0.78

mappedBy

0.77

ContentAsync

0.77

 nahilalakip

0.76

 autorytatywna

0.75

Activations Density 0.204%

superlative adjectives and phrases indicating extremes

No Comments

No Known Activations