INDEX

Explanations

phrases indicating formal statements or conditions

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

Personendaten

-1.12

ніципалі

-0.78

ContentAsync

-0.76

 '\\;'

-0.71

 CreateTagHelper

-0.69

AndEndTag

-0.69

 ویکی‌پدیا

-0.68

addCriterion

-0.65

Diwedd

-0.63

antMatchers

-0.61

POSITIVE LOGITS

 mêmes

0.59

 financières

0.55

 tromper

0.55

 tố

0.54

 bonnes

0.54

 législ

0.54

trate

0.53

 seguenti

0.51

 samme

0.51

 vorstellen

0.50

Activations Density 0.891%

phrases indicating formal statements or conditions

No Comments

No Known Activations