INDEX

Explanations

references to the English language and its significance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 lenker

-0.87

Datuak

-0.86

tagHelperRunner

-0.86

OGND

-0.84

الحياه

-0.82

 ویکی‌پدیای

-0.82

μβρίου

-0.79

InSection

-0.78

Personensuche

-0.78

 iprot

-0.77

POSITIVE LOGITS

 English

0.81

</b>

0.76

 ENGLISH

0.75

</i>

0.73

 Henry

0.66

 engl

0.66

man

0.65

ffffff

0.64

Dodge

0.62

 Godfrey

0.62

Activations Density 0.160%

references to the English language and its significance in various contexts

No Comments

No Known Activations