INDEX

Explanations

terms related to standardization and normality in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

TagHelper

-0.72

pezifische

-0.65

pezif

-0.64

 AssemblyTitle

-0.60

epres

-0.60

 AttributeSet

-0.59

rungsseite

-0.57

AnchorStyles

-0.56

lapsingToolbar

-0.55

 Protobuf

-0.54

POSITIVE LOGITS

 ordinary

1.19

ordinary

1.07

 Ordinary

1.04

Ordinary

1.03

 gewöhn

1.03

 zwyk

1.01

 normale

0.99

 normal

0.97

 normalen

0.94

normal

0.92

Activations Density 0.710%

terms related to standardization and normality in various contexts

No Comments

No Known Activations