INDEX

Explanations

references to educational qualifications and degrees

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 المعيارى

-0.59

CompilerServices

-0.50

alanta

-0.43

DebuggerNonUser

-0.42

onshire

-0.42

 onPostExecute

-0.41

hasMoreElements

-0.41

setColumn

-0.41

klo

-0.39

 وتسجيلات

-0.39

POSITIVE LOGITS

 degree

1.25

 degrees

1.19

 Degree

1.16

degree

1.08

Degree

1.06

PhD

1.03

 Degrees

0.99

degrees

0.96

 DEGREE

0.94

Ph

0.93

Activations Density 0.093%

references to educational qualifications and degrees

No Comments

No Known Activations