INDEX

Explanations

phrases that indicate processes or sequences involving transitions or transformations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

lardır

-0.48

DockStyle

-0.47

 dietro

-0.42

ът

-0.41

Outside

-0.41

Zacks

-0.41

 outside

-0.41

 Outside

-0.40

 acima

-0.40

outside

-0.40

POSITIVE LOGITS

 hindurch

1.22

through

1.11

 through

1.06

Through

0.94

THROUGH

0.92

 THROUGH

0.91

 Through

0.90

tagHelperRunner

0.89

 heen

0.89

 channels

0.81

Activations Density 0.166%

phrases that indicate processes or sequences involving transitions or transformations

No Comments

No Known Activations