INDEX

Explanations

references to time or duration, specifically phrases that include the word "years."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

MethodManager

-0.81

anair

-0.75

FormTagHelper

-0.73

BeginContext

-0.73

 חיצוניים

-0.71

енча

-0.71

AndEndTag

-0.71

Contours

-0.68

 INTERESAR

-0.67

PhysRevLett

-0.67

POSITIVE LOGITS

 years

1.05

Years

0.86

years

0.80

 Years

0.79

 decades

0.74

 YEARS

0.70

YEARS

0.65

 abuse

0.59

 jaren

0.57

 hours

0.49

Activations Density 0.208%

references to time or duration, specifically phrases that include the word "years."

No Comments

No Known Activations