INDEX

Explanations

numerical data or values in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

<em>

-0.71

<strong>

-0.70

<u>

-0.67

-0.63

-0.62

-0.60

-0.59

-0.58

-0.55

-0.54

POSITIVE LOGITS

yntaxException

1.08

NUMX

1.01

 Numerade

0.89

QMetaType

0.89

.*")]

0.88

"]}

0.86

 تانيه

0.84

"])

0.84

uttavia

0.83

contentLoaded

0.83

Activations Density 0.004%

numerical data or values in the text

No Comments

No Known Activations