INDEX

Explanations

references to episodes and their specific details within a television series

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للمعارف

-0.81

 CreateTagHelper

-0.64

хьтан

-0.57

 BoxDecoration

-0.54

tagHelperRunner

-0.54

Bakgrunnsstoff

-0.53

 Majefty

-0.52

rungsseite

-0.51

unknownFields

-0.50

 Autorisations

-0.49

POSITIVE LOGITS

 episode

0.90

 episodes

0.80

Episode

0.68

episode

0.67

 Episode

0.67

 episodio

0.61

 épisode

0.60

 episodi

0.60

pisode

0.56

 Episodes

0.56

Activations Density 0.261%

references to episodes and their specific details within a television series

No Comments

No Known Activations