INDEX

Explanations

quantifiers and comparative phrases in scientific contexts

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

Past tense verbs

np_acts-logits-general · gemini-2.0-flash

determined values and measurements

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

 loose

-0.48

ValueGeneration

-0.46

 AttributeSet

-0.45

̀nh

-0.45

startActivity

-0.45

üyor

-0.45

 الحره

-0.44

Har

-0.44

addLast

-0.44

Enf

-0.43

POSITIVE LOGITS

tvguidetime

0.98

httphttps

0.71

 calculated

0.69

URLException

0.67

 determined

0.65

 Normdatei

0.63

 détermin

0.63

MENAFN

0.63

determined

0.62

 DETERMINATION

0.62

Activations Density 0.721%

quantifiers and comparative phrases in scientific contexts

Past tense verbs

determined values and measurements

No Comments

No Known Activations