INDEX

Explanations

occurrences of the word "pri" in various contexts

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

 Normdatei

-0.77

ImageContext

-0.71

tinyos

-0.70

BnF

-0.69

ulemon

-0.67

 Rockland

-0.66

 emocion

-0.66

GOB

-0.64

 Waterman

-0.64

 meningitis

-0.64

POSITIVE LOGITS

 при

1.70

При

1.67

 При

1.50

при

1.43

 ПРИ

1.35

 przy

1.25

 Při

1.18

 Przy

1.18

 při

1.14

Przy

1.14

Activations Density 0.030%

occurrences of the word "pri" in various contexts

No Comments

No Known Activations