INDEX

Explanations

negative statements and exclamatory responses

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

 AspNetCore

-0.59

 Königreich

-0.57

 isInitialized

-0.57

visel

-0.56

цездатний

-0.56

hoga

-0.54

GeneratedCode

-0.53

Portail

-0.53

__':

-0.52

 makeStyles

-0.52

POSITIVE LOGITS

adaptiveStyles

0.62

 Paglinawan

0.61

 dedans

0.60

Personendaten

0.59

 scattata

0.58

 Privacidade

0.57

 <<<<<<<<<<<<<<

0.56

rawtypes

0.56

évaluateur

0.55

Gön

0.55

Activations Density 0.242%

negative statements and exclamatory responses

No Comments

No Known Activations