INDEX

Explanations

proper nouns and significant entities within a text

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

WithIOException

-1.08

 utafitiHapana

-0.85

 saites

-0.85

 pinulongan

-0.85

+#+#

-0.80

 estekak

-0.77

="@+

-0.76

脚注の使い方

-0.73

 Wikimedijinoj

-0.70

 HasFactory

-0.67

POSITIVE LOGITS

<eos>

0.59

↵↵↵↵

0.55

 Senado

0.52

↵↵

0.51

↵↵↵

0.46

daj

0.45

...

0.45

uvwxyz

0.45

Also

0.43

 Firefly

0.43

Activations Density 0.728%

proper nouns and significant entities within a text

No Comments

No Known Activations