INDEX

Explanations

numeric representations and descriptions of quantity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

 EconPapers

-0.83

 <=",

-0.81

 Theſe

-0.78

 ddelweddau

-0.78

 houſe

-0.75

 discography

-0.74

 chrétiens

-0.74

 purpoſe

-0.74

 CreateTagHelper

-0.73

 للمعارف

-0.73

POSITIVE LOGITS

 different

1.04

teen

0.89

 separate

0.88

 distinct

0.86

0.81

zehn

0.76

 more

0.72

TEEN

0.72

 large

0.72

 total

0.71

Activations Density 0.618%

numeric representations and descriptions of quantity

No Comments

No Known Activations