INDEX

Explanations

references to violence in media and fiction, particularly in cartoons and their effects

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

 AssemblyProduct

-0.57

äldrar

-0.54

khana

-0.53

loem

-0.50

thenia

-0.49

aronder

-0.49

λια

-0.48

 metabo

-0.48

 '\\;'

-0.48

غان

-0.47

POSITIVE LOGITS

 fictional

1.10

 fictitious

0.97

 unrealistic

0.94

 unreal

0.92

 ficción

0.92

 fantasy

0.88

 fiction

0.86

 imaginary

0.79

Fic

0.77

fik

0.77

Activations Density 0.715%

references to violence in media and fiction, particularly in cartoons and their effects

No Comments

No Known Activations