INDEX

Explanations

instances indicating the beginning of a new section or segment in a document

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

</strong>

-0.52

-0.47

 فريبيس

-0.46

tvguidetime

-0.45

 […]

-0.44

 combination

-0.42

</b>

-0.42

styleable

-0.42

politico

-0.42

częściej

-0.41

POSITIVE LOGITS

 Roskov

0.82

AddHtmlAttribute

0.75

󠁿

0.69

 مشين

0.68

ValueStyle

0.67

 EnglishChoose

0.67

 tartalomajánló

0.66

 cherchés

0.65

 дописавши

0.64

 doInBackground

0.64

Activations Density 0.359%

instances indicating the beginning of a new section or segment in a document

No Comments

No Known Activations