INDEX

Explanations

phrases indicating conditions or assumptions based on prior statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 πάνω

-0.51

hiza

-0.50

 sacco

-0.48

znik

-0.46

endaftaran

-0.45

 Normandie

-0.44

代わりに

-0.43

ldb

-0.42

Переваги

-0.42

act

-0.42

POSITIVE LOGITS

 considering

1.16

considering

1.15

Considering

1.13

 Considering

1.13

 mengingat

1.01

 Given

0.99

ostante

0.96

Given

0.95

given

0.95

 محفوظة

0.95

Activations Density 0.242%

phrases indicating conditions or assumptions based on prior statements

No Comments

No Known Activations