INDEX

Explanations

references to user experience and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

zugehen

-0.71

mädchen

-0.68

 dõi

-0.67

betical

-0.66

 RoHS

-0.62

шаго

-0.62

 prioridad

-0.61

 priorité

-0.61

subsid

-0.61

abz

-0.60

POSITIVE LOGITS

 experience

2.58

 experiences

2.42

 Experience

2.30

Experience

2.26

 EXPERIENCE

2.21

experience

2.21

 Experiences

2.20

EXPERIENCE

2.12

 experien

2.08

experiences

2.05

Activations Density 0.050%

references to user experience and interactions

No Comments

No Known Activations