INDEX

Explanations

repetitive patterns of the word "almost"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 وتسجيلات

-0.79

 kaarangay

-0.68

 <=",

-0.66

 विश्वसनीयता

-0.64

SBATCH

-0.64

 AssemblyTitle

-0.64

 astfel

-0.58

IContainer

-0.56

 autrement

-0.55

 Roughly

-0.55

POSITIVE LOGITS

 identical

0.75

 certainly

0.72

 imperceptible

0.69

 universally

0.67

 exclusively

0.67

certainly

0.64

 impossible

0.63

тельном

0.61

weds

0.61

 everyone

0.60

Activations Density 0.239%

repetitive patterns of the word "almost"

No Comments

No Known Activations