INDEX

Explanations

references to general items or concepts

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

 lágrimas

-0.84

 gales

-0.84

 hanem

-0.83

 Heber

-0.82

UpInside

-0.82

 larmes

-0.82

adecimal

-0.80

 Sapphire

-0.78

 วาด

-0.78

 fhew

-0.78

POSITIVE LOGITS

 things

2.66

Things

2.31

 Things

2.30

 THINGS

2.22

 thing

2.18

things

2.14

 Thing

1.95

 THING

1.85

Thing

1.78

THINGS

1.75

Activations Density 0.060%

references to general items or concepts

No Comments

No Known Activations