INDEX

Explanations

punctuation marks and formatting symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

par

-0.45

"=>"

-0.41

zu

-0.40

Zu

-0.40

```

-0.40

 last

-0.40

condition

-0.39

Kal

-0.38

障

-0.38

kur

-0.38

POSITIVE LOGITS

 للاسماء

0.89

 nahilalakip

0.88

 INTERESAR

0.88

 kasarigan

0.83

expandindo

0.83

 Signalez

0.82

StoryboardSegue

0.79

 NUKAT

0.78

InjectAttribute

0.77

 виправивши

0.74

Activations Density 0.030%

punctuation marks and formatting symbols

No Comments

No Known Activations