INDEX

Explanations

references to communication channels in various contexts

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

es

-0.69

swiper

-0.69

 Mortimer

-0.66

י

-0.66

ydi

-0.65

 slow

-0.62

 sourire

-0.62

McK

-0.61

ES

-0.61

POSITIVE LOGITS

 channels

1.67

Channels

1.54

channels

1.53

 Channels

1.52

 channel

1.46

 Channel

1.43

 CHANNEL

1.39

CHANNEL

1.31

Channel

1.28

 channe

1.28

Activations Density 0.070%

references to communication channels in various contexts

No Comments

No Known Activations