INDEX

Explanations

references to geopolitical events and characters involved in them

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

Followed by prepositions or punctuation

np_acts-logits-general · gemini-2.0-flash

pronouns and specific entities

np_acts-logits-general · gemini-2.5-flash-lite

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

 оригіналу

-0.71

IsMutable

-0.69

///</

-0.69

 '\\;'

-0.67

webElementXpaths

-0.65

GOTREF

-0.65

+#+#

-0.64

 ویکی‌پدی

-0.64

الحياه

-0.63

 otomatig

-0.63

POSITIVE LOGITS

 into

0.67

 adecuadamente

0.62

 with

0.60

 adequad

0.58

 accordingly

0.57

 through

0.55

 efficacement

0.55

 hagas

0.55

 eccell

0.55

 econó

0.53

Activations Density 0.441%

references to geopolitical events and characters involved in them

Followed by prepositions or punctuation

pronouns and specific entities

No Comments

No Known Activations