INDEX

Explanations

occurrences of the prefix "mo"

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

IFrame

Link

Negative Logits

 دیکھیے

-0.96

windowFixed

-0.94

 Werth

-0.86

bootstrapcdn

-0.84

LookAnd

-0.83

yntaxException

-0.82

/>\

-0.81

DockStyle

-0.80

+#+

-0.79

encodeWith

-0.79

POSITIVE LOGITS

mo

1.94

mo

0.99

Mo

0.90

MO

0.89

Mo

0.88

moed

0.73

MO

0.67

モ

0.66

mog

0.66

moz

0.63

Activations Density 0.024%

occurrences of the prefix "mo"

No Known Activations