INDEX

Explanations

phrases indicating familiarity or habituation to experiences or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 myſelf

-0.75

 وتسجيلات

-0.70

Hentet

-0.68

 Reſ

-0.67

 >=",

-0.67

 ſind

-0.66

 Diſ

-0.64

 Houſe

-0.63

 Krim

-0.62

 ſtate

-0.62

POSITIVE LOGITS

 accustomed

1.03

 привы

0.95

 acostumb

0.91

 gewohnt

0.82

 familiar

0.77

habitude

0.74

 habitu

0.73

习惯

0.72

 habitual

0.72

familiar

0.69

Activations Density 0.103%

phrases indicating familiarity or habituation to experiences or situations

No Comments

No Known Activations