INDEX

Explanations

words indicating skepticism or concern

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

Expressing certainty or doubt

np_acts-logits-general · gemini-2.0-flash

expressing certainty or doubt

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 kaynağından

-0.70

WriteTagHelper

-0.68

이버

-0.64

ContentLoaded

-0.63

ymal

-0.63

MLLoader

-0.62

новништво

-0.61

بوابة

-0.61

Bronnen

-0.58

DllImport

-0.58

POSITIVE LOGITS

 that

0.80

 there

0.72

addCriterion

0.71

 they

0.65

jooq

0.65

 bahwa

0.62

 bahawa

0.56

we

0.53

 about

0.52

 africains

0.52

Activations Density 0.308%

words indicating skepticism or concern

Expressing certainty or doubt

expressing certainty or doubt

No Comments

No Known Activations