INDEX

Explanations

references to places, particularly in the context of studies or descriptions involving locations

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

"place"

np_acts-logits-general · gemini-2.0-flash

place followed by of or articles

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 scolaires

-0.99

 HasFactory

-0.86

WebVitals

-0.81

StructEnd

-0.77

Erreferentziak

-0.76

󠁴

-0.76

 Normdatei

-0.75

 domestiques

-0.74

OGND

-0.74

setDo

-0.73

POSITIVE LOGITS

 placed

0.85

 Place

0.83

Place

0.80

 PLACE

0.73

PLACE

0.73

place

0.72

Placed

0.72

 PLAC

0.71

 Placed

0.71

placed

0.71

Activations Density 0.166%

references to places, particularly in the context of studies or descriptions involving locations

"place"

place followed by of or articles

No Comments

No Known Activations