INDEX

Explanations

conditional statements that indicate dependence on various factors

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Fit

-0.52

gen

-0.51

 Real

-0.50

 moldes

-0.49

sinon

-0.48

lación

-0.48

olia

-0.48

gerald

-0.47

 reverse

-0.47

actable

-0.47

POSITIVE LOGITS

 depends

1.41

 Depends

1.40

Depends

1.32

depends

1.28

 depende

1.23

 depended

1.20

 depend

1.15

 dépend

1.11

 zależy

1.10

 dipende

1.09

Activations Density 0.257%

conditional statements that indicate dependence on various factors

No Comments

No Known Activations