INDEX

Explanations

references to poverty or poor quality

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

stuk

-0.66

 Alves

-0.64

aliyun

-0.63

 Bellini

-0.61

-0.59

uggets

-0.59

bootstrapcdn

-0.59

uVar

-0.58

ędzy

-0.58

jago

-0.58

POSITIVE LOGITS

 POOR

1.29

 Poor

1.26

poor

1.19

 poor

1.19

Poor

1.18

 poorer

1.11

Datuak

0.98

 poorly

0.84

 poorest

0.83

 Poverty

0.81

Activations Density 0.048%

references to poverty or poor quality

No Comments

No Known Activations