INDEX

Explanations

words and phrases related to critique and evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

tagez

-0.67

Morfologia

-0.58

жели

-0.57

adaptiveStyles

-0.57

 invokingState

-0.57

RegressionTest

-0.56

 EconPapers

-0.56

glTexCoord

-0.55

 sanitaires

-0.55

 vectorielles

-0.53

POSITIVE LOGITS

 somewhat

0.65

 trifle

0.62

matchCondition

0.59

少々

0.57

 pretty

0.55

лади

0.55

Ahem

0.55

 abit

0.54

/*

0.54

;)

0.53

Activations Density 0.248%

words and phrases related to critique and evaluation

No Comments

No Known Activations