INDEX

Explanations

references to academic grades or educational assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 فريبيس

-0.85

prefixer

-0.83

 Esch

-0.81

 Rossetti

-0.79

์ตูน

-0.79

 Barnett

-0.79

UpInside

-0.77

ropolis

-0.76

 مرئيه

-0.76

gance

-0.76

POSITIVE LOGITS

 Grades

0.92

 Grade

0.90

Grades

0.89

 GRADE

0.88

Grade

0.85

 grades

0.81

grades

0.80

 Coon

0.76

grade

0.74

 Textbook

0.74

Activations Density 0.535%

references to academic grades or educational assessments

No Comments

No Known Activations