INDEX

Explanations

proper nouns and specific identifiers related to location, people, and entities

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

ècie

-0.79

Enumerator

-0.75

VAN

-0.72

 rest

-0.69

Hä

-0.69

FromFile

-0.68

hä

-0.68

Tu

-0.68

-0.67

 Carlos

-0.66

POSITIVE LOGITS

$")

1.00

Efq

1.00

fjspx

0.96

?")

0.96

endfor

0.95

$}}

0.94

 MonoBehaviour

0.94

)‏

0.94

 SwiftUI

0.94

 ―――――

0.93

Activations Density 1.540%

proper nouns and specific identifiers related to location, people, and entities

No Comments

No Known Activations