INDEX

Explanations

terms related to differentiation, separation, and distinction

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

"differentiation" and "separation"

np_acts-logits-general · gemini-2.0-flash

distinguishing from

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 EconPapers

-0.66

 disambiguazione

-0.64

Enllaces

-0.61

Cyfeiriadau

-0.61

writerow

-0.59

UpInside

-0.59



-0.58

 kasarigan

-0.58

ESTAMP

-0.58

 Winaray

-0.57

POSITIVE LOGITS

 from

2.57

from

1.83

 från

1.57

 FROM

1.56

จาก

1.51

 khỏi

1.43

 dari

1.43

From

1.39

 From

1.38

 от

1.34

Activations Density 0.401%

terms related to differentiation, separation, and distinction

"differentiation" and "separation"

distinguishing from

No Comments

No Known Activations