INDEX

Explanations

references to coffee and coffee-related establishments

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

makeConstraints

-0.73

 Rahim

-0.69

IsPostBack

-0.69

Eze

-0.69

떻

-0.69

swire

-0.68

 JsonResult

-0.68

trise

-0.66

 Antrim

-0.66

 Xunit

-0.66

POSITIVE LOGITS

 coffee

2.60

Coffee

2.38

 Coffee

2.35

coffee

2.35

 coffees

2.11

 COFFEE

2.09

 coffe

2.03

 Coffe

1.85

FFEE

1.60

 espresso

1.58

Activations Density 0.029%

references to coffee and coffee-related establishments

No Comments

No Known Activations