INDEX

Explanations

numerical values and legal references

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

 ویکی‌پدی

-1.03

AsUp

-0.91

 виправивши

-0.88

Билгалдахарш

-0.84

 disambiguazione

-0.82

 Meksiku

-0.81

PHeader

-0.80

انيف

-0.79

rungsseite

-0.79

verifyException

-0.77

POSITIVE LOGITS

1.17

 eight

0.75

six

0.72

ten

0.71

 seven

0.71

 five

0.70

 nine

0.69

 eighteen

0.67

 four

0.66

 twelve

0.65

Activations Density 1.353%

numerical values and legal references

No Comments

No Known Activations