INDEX

Explanations

terms related to indicating or signaling something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 Rowe

-0.69

wn

-0.68

farlane

-0.66

tw

-0.63

repos

-0.62

Longest

-0.62

al

-0.61

пло

-0.61

brunn

-0.60

die

-0.59

POSITIVE LOGITS

 INDIC

1.47

 Indicates

1.35

 Indicators

1.29

 indicators

1.26

Indicates

1.26

 Indicator

1.26

Indicators

1.24

 Indicate

1.21

INDICATOR

1.20

indicator

1.19

Activations Density 0.087%

terms related to indicating or signaling something

No Comments

No Known Activations