INDEX

Explanations

symbols and punctuation marks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

DockStyle

-0.76

 BoxFit

-0.70

 snippetHide

-0.70

']>

-0.63

 CreateTagHelper

-0.61

ULO

-0.59

AutoresizingMask

-0.58

queryInterface

-0.58

 canst

-0.57

ocities

-0.57

POSITIVE LOGITS

를

0.70

에

0.60

を

0.58

 being

0.58

 aside

0.51

와

0.50

ile

0.49

க்கு

0.48

 için

0.47

に

0.47

Activations Density 0.023%

symbols and punctuation marks

No Comments

No Known Activations