INDEX

Explanations

specific entities or notable records, particularly those related to achievements or milestones

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

writeFieldEnd

-0.96

 <=",

-0.79

UnusedPrivate

-0.79

 مشين

-0.75

 تضيفلها

-0.75

 Савезне

-0.75

OrBuilder

-0.73

 lenker

-0.72

yntaxException

-0.69

PyExc

-0.69

POSITIVE LOGITS

 rekord

0.65

 record

0.62

 recorded

0.59

 рекор

0.54

 RECORD

0.53

 ooit

0.52

record

0.52

 Rekord

0.52

اریخ

0.48

 Record

0.46

Activations Density 0.138%

specific entities or notable records, particularly those related to achievements or milestones

No Comments

No Known Activations