INDEX

Explanations

words related to boosting or elevating actions or conditions

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

BeginContext

-0.66

 الحره

-0.60

Dum

-0.59

 EconPapers

-0.58

TagMode

-0.56

 kasarigan

-0.53

hadapi

-0.52

Shops

-0.52

CDCl

-0.51

sơ

-0.51

POSITIVE LOGITS

 increase

3.66

 increases

3.32

increase

3.29

 Increase

3.25

Increase

3.21

 increased

2.99

 Increases

2.98

increases

2.91

Increases

2.84

 INCREASE

2.84

Activations Density 0.114%

words related to boosting or elevating actions or conditions

No Comments

No Known Activations