INDEX

Explanations

negations or rejections in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ing

-0.87

ené

-0.82

ی

-0.81

 Dougherty

-0.75

-0.72

-0.71

 Alcott

-0.71

خصة

-0.71

 Alva

-0.69

yny

-0.69

POSITIVE LOGITS

ly

1.12

verwijspagina

1.06

 itſelf

1.03

makeConstraints

0.99

Efq

0.98

Ire

0.96

usehen

0.93

 himſelf

0.93

Eme

0.92

 myſelf

0.92

Activations Density 0.028%

negations or rejections in various contexts

No Comments

No Known Activations