INDEX

Explanations

emphatic expressions of totality or completeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 phosphory

-0.56

 marquées

-0.55

 PopupWindow

-0.55

 heur

-0.54

imath

-0.54

ijão

-0.52

IAA

-0.52

gridx

-0.51

chkin

-0.51

有料

-0.51

POSITIVE LOGITS

 completely

3.86

 entirely

3.78

 totally

3.48

 Completely

3.42

completely

3.27

Completely

3.20

 wholly

2.93

 Totally

2.90

totally

2.87

 completamente

2.77

Activations Density 0.146%

emphatic expressions of totality or completeness

No Comments

No Known Activations