INDEX

Explanations

references to expert educators and their credentials

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

 ProtoMessage

-0.59

########.

-0.55

AnchorStyles

-0.54

Espèce

-0.54

رشف

-0.52

IsContent

-0.52

ScopeManager

-0.50

 pinulongan

-0.50

RegressionTest

-0.48

principalColumn

-0.48

POSITIVE LOGITS

 expertos

0.47

 EXPERT

0.47

 expert

0.46

 expertise

0.43

expertise

0.43

 esperti

0.41

uação

0.41

 TEACHING

0.40

 insegn

0.40

 especializada

0.40

Activations Density 0.010%

references to expert educators and their credentials

No Comments

No Known Activations