INDEX

Explanations

references to specific numerical data or scientific details

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

migrationBuilder

-0.51

énario

-0.49

Gizmos

-0.45

 Word

-0.44

ScopeManager

-0.43

autaire

-0.43

 cerimonia

-0.42

orElseThrow

-0.42

真好

-0.42

Phal

-0.42

POSITIVE LOGITS

msgTypes

0.36

cline

0.36

 lustig

0.34

ությ

0.34

entier

0.33

')")

0.32

 recensement

0.32

 SEDS

0.31

 "..\..\

0.31

SourceChecksum

0.31

Activations Density 0.592%

references to specific numerical data or scientific details

No Comments

No Known Activations