INDEX

Explanations

assignments and object initializations in code

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

 متعلقه

-0.54

Gön

-0.51

uxxxx

-0.50

 reliefs

-0.50

ɵɵelementEnd

-0.49

endpush

-0.49



-0.49

xaml

-0.49

 quota

-0.48

argout

-0.48

POSITIVE LOGITS

awtextra

0.55

GIVEREF

0.47

RegressionTest

0.43

setVerticalGroup

0.40

 inconn

0.40

 jangka

0.39

 vectorielles

0.39

ándote

0.39

 frança

0.38

 sengaja

0.38

Activations Density 0.098%

assignments and object initializations in code

No Comments

No Known Activations