INDEX

Explanations

indicators of research and academic diligence

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

Preceding tokens of words like "research" or "dim"

np_acts-logits-general · gemini-2.0-flash

doing research

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

urlpatterns

-0.52

XmlAccessorType

-0.51

 يتيمه

-0.47

 artificiales

-0.43

 CreateTagHelper

-0.42

walde

-0.42

icola

-0.41

hog

-0.41

addContainerGap

-0.41

nictví

-0.40

POSITIVE LOGITS

 research

2.01

 researched

1.86

 researching

1.86

research

1.80

 Research

1.69

Research

1.67

 researches

1.60

 RESEARCH

1.57

RESEARCH

1.53

 investigación

1.30

Activations Density 0.184%

indicators of research and academic diligence

Preceding tokens of words like "research" or "dim"

doing research

No Comments

No Known Activations