INDEX

Explanations

conditional statements and hypothetical scenarios

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

 surla

-0.55

ParallelGroup

-0.55

matchCondition

-0.53

 głównie

-0.52

󠁢

-0.51

 interessanti

-0.50

 onderwijs

-0.49

WriteBarrier

-0.49

 prawda

-0.49

 pourront

-0.48

POSITIVE LOGITS

 будто

0.50

OCCURRED

0.46

 disambiguazione

0.41

まるで

0.40

 Мексичка

0.39

AutoScaleMode

0.39

 jakby

0.37

仿佛

0.36

 EconPapers

0.35

หมือน

0.33

Activations Density 0.180%

conditional statements and hypothetical scenarios

No Comments

No Known Activations