INDEX

Explanations

phrases related to summaries and information sharing

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

followed by a list or summary

np_acts-logits-general · gemini-2.0-flash

introducing lists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LookAnd

-0.71

medriver

-0.65

 الرياضيه

-0.65

 ddelweddau

-0.61

Історія

-0.60

writeFieldEnd

-0.56

glClear

-0.56

urlpatterns

-0.55

̍t

-0.53

Économie

-0.51

POSITIVE LOGITS

 some

1.42

 några

1.11

 algunos

1.10

 alguns

1.09

 algunas

1.08

 quelques

1.08

 algumas

1.05

some

1.04

 briefly

1.03

Some

0.98

Activations Density 0.340%

phrases related to summaries and information sharing

followed by a list or summary

introducing lists

No Comments

No Known Activations