INDEX

Explanations

relationships between concepts and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Theſe

-0.79

 becauſe

-0.65

Efq

-0.64

.*")]

-0.63

 raiſ

-0.62

 Cæsar

-0.61

 ſever

-0.61

 ſeveral

-0.61

 uſed

-0.60

 faſt

-0.59

POSITIVE LOGITS

 therefore

0.55

 nên

0.54

Rightarrow

0.53

it

0.51

 makes

0.51

so

0.51

 समीक्षाएं

0.50

 permite

0.50

 allow

0.50

itinéraire

0.49

Activations Density 0.549%

relationships between concepts and their implications

No Comments

No Known Activations