INDEX

Explanations

words related to statistical comparisons and ratios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

None

-0.55

-0.54

none

-0.53

autres

-0.53

 None

-0.50

 inga

-0.50

neither

-0.50

these

-0.49

Any

-0.47

 none

-0.47

POSITIVE LOGITS

 everyone

1.22

 everybody

1.15

 everything

1.08

 Everybody

1.07

everybody

1.03

EVERY

1.03

Everybody

1.02

everyone

1.00

Everyone

0.98

 Everyone

0.98

Activations Density 0.202%

words related to statistical comparisons and ratios

No Comments

No Known Activations