INDEX

Explanations

negations and expressions of doubt

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

 AssemblyCulture

-0.78

GEBURTSDATUM

-0.70

OGND

-0.60

 invokingState

-0.59

 ProtoMessage

-0.56

LookAnd

-0.54

 AssemblyVersion

-0.51

évaluateur

-0.50

Controllo

-0.50

DockStyle

-0.49

POSITIVE LOGITS

Tikang

0.47

 Reporters

0.44

 LIRE

0.42

 pomy

0.42

news

0.41

 reporter

0.40

 news

0.40

leneck

0.39

UserScript

0.39

 NEWS

0.39

Activations Density 0.077%

negations and expressions of doubt

No Comments

No Known Activations