INDEX

Explanations

specific references to individuals or entities 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 @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

expandindo

-0.86

LookAnd

-0.74

 صوتيه

-0.69

 externi

-0.69

ніципалі

-0.67

ValueStyle

-0.67

Erstellt

-0.67

-------------</

-0.66

 snippetHide

-0.64

astify

-0.63

POSITIVE LOGITS

 noires

0.52

 fermés

0.52

 étrang

0.50

creativecommons

0.49

 ouverts

0.49

 invités

0.48

ménage

0.47

 tomber

0.45

 tebal

0.45

ocene

0.45

Activations Density 1.302%

specific references to individuals or entities in various contexts

No Comments

No Known Activations