INDEX

Explanations

numerical expressions and mathematical notation

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

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

 kasarigan

-0.88

RegressionTest

-0.80

Personensuche

-0.77

 tartalomajánló

-0.73

Datuak

-0.71

 Италијани

-0.70

 estekak

-0.67

SourceChecksum

-0.67

 سكانية

-0.65

),"

-0.63

POSITIVE LOGITS

 pleaſure

0.67

ousand

0.62

 ſmall

0.60

 perſon

0.59

 ſtate

0.59

fastjson

0.59

 Theſe

0.58

SneakyThrows

0.58

 fhort

0.58

 normaux

0.57

Activations Density 0.936%

numerical expressions and mathematical notation

No Comments

No Known Activations