INDEX

Explanations

terms related to flat or linear concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

yntaxException

-0.66

 ***!

-0.60

sizeCache

-0.56

 Momente

-0.55

••••

-0.55

LayoutStyle

-0.55

 personnaliser

-0.54

 découv

-0.52

]--;

-0.51

CrossRef

-0.50

POSITIVE LOGITS

flat

0.87

 flat

0.84

Flat

0.79

FLAT

0.79

 Flat

0.79

 autorytatywna

0.75

 linear

0.74

 Linear

0.73

 FLAT

0.73

Linear

0.73

Activations Density 0.105%

terms related to flat or linear concepts

No Comments

No Known Activations