INDEX

Explanations

phrases indicating habitual actions or states of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Feign

-0.64

vő

-0.62

 weighed

-0.60

 ounce

-0.58

 وتسجيلات

-0.56

 회원

-0.56

lamabad

-0.55

 Pingback

-0.55

 FAIL

-0.54

RPM

-0.54

POSITIVE LOGITS

 accustomed

0.92

 acostumb

0.78

Comfortable

0.76

 comfortable

0.74

 acost

0.73

comfortable

0.72

habitude

0.68

慣れて

0.67

 Comfortable

0.67

 alış

0.66

Activations Density 0.096%

phrases indicating habitual actions or states of being

No Comments

No Known Activations