INDEX

Explanations

text marked as the beginning of a document or section

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

of

-0.77

ly

-0.57

 from

-0.56

of

-0.56

お

-0.55

-0.54

一

-0.52

お金

-0.52

人気

-0.51

POSITIVE LOGITS

principalColumn

0.90

 мәкал

0.90

 فريبيس

0.89

ſelf

0.86

)”.

0.85

 estekak

0.85

IsMutable

0.85

 EconPapers

0.85

ſelves

0.84

 esternos

0.84

Activations Density 0.014%

text marked as the beginning of a document or section

No Comments

No Known Activations