INDEX

Explanations

complex scientific terminology and data representation

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

 ***!

-0.69

SourceChecksum

-0.62

tagHelperRunner

-0.61

Tikang

-0.59

invokeLater

-0.56

EditorBrowsable

-0.52

URLException

-0.51

 Taktlose

-0.50

 propOrder

-0.50

 AssemblyProduct

-0.49

POSITIVE LOGITS

 gynhyrchwyd

0.78

principalColumn

0.59

 ones

0.56

trab

0.55

خرى

0.55

umon

0.54

yns

0.54

 saites

0.53

뀜

0.53

iettivo

0.52

Activations Density 1.237%

complex scientific terminology and data representation

No Comments

No Known Activations