INDEX

Explanations

phrases or terms related to estimation and quantification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

“

-0.66

-0.65

’

-0.64

</i>

-0.61

</b>

-0.61

-0.59

-0.58

-0.57

-0.56

POSITIVE LOGITS

 Estimates

1.21

 estimates

1.19

 estimat

1.18

Estimates

1.15

 Estimate

1.15

 Esti

1.11

 itſelf

1.10

 estimate

1.09

 iſt

1.08

makeConstraints

1.06

Activations Density 0.140%

phrases or terms related to estimation and quantification

No Comments

No Known Activations