INDEX

Explanations

instances of the letter 'R' and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 standard

-0.48

 Standard

-0.47

agerie

-0.46

Step

-0.46

 Largo

-0.46

 continúas

-0.43

 Mena

-0.42

annu

-0.42

dataclass

-0.42

 Step

-0.42

POSITIVE LOGITS

 onCancelled

0.67

 CreateTagHelper

0.67

AtIndexPath

0.63

 ویکی‌پدیا

0.61

FunctionFlags

0.61

InstanceState

0.61

 InputDecoration

0.58

aise

0.57

 विश्वसनीयता

0.56

 lèvres

0.55

Activations Density 0.281%

instances of the letter 'R' and its variations in different contexts

No Comments

No Known Activations