INDEX

Explanations

the word "all" in various contexts, indicating an emphasis on inclusivity or totality

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

jstor

-0.71

 Moskva

-0.70

URBANA

-0.69

 Ferne

-0.69

Figure

-0.68

 tempfile

-0.68

 sẻ

-0.68

➜

-0.67

 Nicosia

-0.67

er

-0.67

POSITIVE LOGITS

all

1.99

ALL

1.82

All

1.66

All

1.58

all

1.43

ALL

1.40

setAll

1.26

ReadAll

1.21

 semua

1.21

 GetAll

1.20

Activations Density 0.145%

the word "all" in various contexts, indicating an emphasis on inclusivity or totality

No Comments

No Known Activations