INDEX

Explanations

terms related to adjustments or changes in quantities or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Zusammen

-0.56

Diwedd

-0.54

aside

-0.53

 Gode

-0.51

friday

-0.50

($)

-0.50

getElementById

-0.49

lexikon

-0.48

vious

-0.48

 OMITTED

-0.48

POSITIVE LOGITS

 become

0.83

 deviennent

0.78

Become

0.78

DockStyle

0.72

 becoming

0.72

值为

0.71

kháu

0.70

變成

0.69

AnchorStyles

0.69

 becomes

0.69

Activations Density 0.378%

terms related to adjustments or changes in quantities or states

No Comments

No Known Activations