INDEX

Explanations

numeric values and their associated formatting

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

↵

-0.76

↵↵↵

-0.72

↵↵↵↵

-0.68

↵↵

-0.66

↵↵↵↵↵

-0.60

 مشين

-0.57

↵↵↵↵↵↵

-0.56

\{\

-0.54

↵↵↵↵↵↵↵↵

-0.52

 "..\..\

-0.50

POSITIVE LOGITS

Subjects

0.63

 للمعارف

0.51

Eksterne

0.50

<<<<<<<

0.48

Subject

0.48

EndProject

0.47

elemField

0.47

Portály

0.47

 onAnimation

0.47

didSet

0.46

Activations Density 0.285%

numeric values and their associated formatting

No Comments

No Known Activations