INDEX

Explanations

instances of the word "round" and its variations, indicating circular or repetitive processes

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

+#+#

-0.96

 &___

-0.84

setupUi

-0.83

 MotionEvent

-0.83

المكان

-0.79

abilia

-0.75

gasus

-0.75

évaluateur

-0.75

Referències

-0.75

closedir

-0.75

POSITIVE LOGITS

 ROUND

1.21

 Rounds

1.21

 rounds

1.13

Round

1.09

Rounds

1.07

round

1.06

 Round

1.04

ROUND

1.03

 Ronde

1.01

rounds

1.00

Activations Density 0.081%

instances of the word "round" and its variations, indicating circular or repetitive processes

No Comments

No Known Activations