INDEX

Explanations

specific technical terms or metrics related to various fields such as healthcare, automotive, and engineering

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 parç

-0.39

vü

-0.37

ẨM

-0.36

 fotografico

-0.36

 antaranya

-0.35

 piatta

-0.35

 sağlar

-0.34

wst

-0.34

 REGARD

-0.34

 spett

-0.33

POSITIVE LOGITS

SourceChecksum

0.60

expandindo

0.59

exitRule

0.58

 Roskov

0.54

 estekak

0.51

WithIOException

0.51

IntoConstraints

0.48

bootstrapcdn

0.47

TagMode

0.47

سطس

0.46

Activations Density 0.287%

specific technical terms or metrics related to various fields such as healthcare, automotive, and engineering

No Comments

No Known Activations