INDEX

Explanations

phrases related to prior references or citations 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 @ 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

Not in Any Lists

No Comments

Negative Logits

TabView

-0.52

-0.51

 even

-0.50

Las

-0.46

las

-0.44

the

-0.44

-0.43

 from

-0.43

Latest

-0.42

POSITIVE LOGITS

ScopeManager

1.01

 aforesaid

0.98

évaluateur

0.96

 myſelf

0.96

 mentioned

0.92

mentioned

0.91

 ſaid

0.90

 aforementioned

0.89

adaptiveStyles

0.88

 itſelf

0.85

Activations Density 0.256%

phrases related to prior references or citations in the text

No Comments

No Known Activations