INDEX

Explanations

questions related to character engagement and development

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

 disambiguazione

-0.61

 settore

-0.59

PYX

-0.56

 CURIAM

-0.56

⁂

-0.56

 Roskov

-0.53

λία

-0.52

 useStyles

-0.52

uracy

-0.51

гії

-0.51

POSITIVE LOGITS

 persona

1.12

 character

1.07

 characters

1.05

 personality

1.03

 Characters

0.97

 personaje

0.97

 personnage

0.97

 portrayed

0.94

 avatar

0.93

 figure

0.93

Activations Density 0.401%

questions related to character engagement and development

No Comments

No Known Activations