INDEX

Explanations

phrases related to negative qualities or criticisms regarding people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

AnimationsModule

-0.79

 незавершена

-0.58

ChromeDriver

-0.58

 Dumas

-0.57

 ddelweddau

-0.54

+:+

-0.54

 StatefulWidget

-0.51

FOLK

-0.51

ecraft

-0.50

ppure

-0.49

POSITIVE LOGITS

 mean

1.00

 rude

0.98

 Mean

0.87

mean

0.85

Mean

0.84

 unfriendly

0.83

 push

0.81

sno

0.79

 judgment

0.76

 standoff

0.74

Activations Density 0.318%

phrases related to negative qualities or criticisms regarding people

No Comments

No Known Activations