INDEX

Explanations

references to hotels and lodging

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UnsafeEnabled

-0.91

yntaxException

-0.74

paksa

-0.66

 barbacoa

-0.66

 SwitchCompat

-0.65

 búsquedas

-0.64

 aans

-0.64

WebVitals

-0.64

 '\\;'

-0.64

||}

-0.64

POSITIVE LOGITS

 hotel

3.15

 hotels

2.94

 Hotel

2.87

hotel

2.81

 HOTEL

2.71

Hotel

2.65

 Hotels

2.65

HOTEL

2.48

Hotels

2.43

hotels

2.33

Activations Density 0.037%

references to hotels and lodging

No Comments

No Known Activations