INDEX

Explanations

conditions related to numeric comparisons or thresholds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

-0.86

-0.83

Clik

-0.77

-0.72

 düş

-0.68

 tart

-0.67

ul

-0.67

styleType

-0.67

ing

-0.67

POSITIVE LOGITS

]>=

1.57

)>=

1.43

>=

1.34

>=

1.21

Efq

1.11

^(@)

1.08

bibfield

1.03

 Majefty

1.01

 myſelf

1.01

BibitemShut

1.00

Activations Density 0.103%

conditions related to numeric comparisons or thresholds

No Comments

No Known Activations