INDEX

Explanations

logical relationships and associations within statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

ValueStyle

-0.81

Datuak

-0.70

évaluateur

-0.70

 مشين

-0.69

 متعلقه

-0.69

IVEREF

-0.68

adaptiveStyles

-0.68

ReusableCell

-0.66

########.

-0.65

multirow

-0.65

POSITIVE LOGITS

 side

0.56

 helft

0.51

 weaker

0.46

どちら

0.45

 alimentaires

0.45

 legales

0.45

 partij

0.45

 jdbcTemplate

0.45

そちら

0.44

 השני

0.44

Activations Density 0.772%

logical relationships and associations within statements

No Comments

No Known Activations