INDEX

Explanations

conversational or narrative elements related to knowledge or stating facts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

AndEndTag

-0.66

SequentialGroup

-0.61

 edelstahl

-0.55

archiviato

-0.55

 Trotzdem

-0.55

 للمعارف

-0.54

슷

-0.54

 becauſe

-0.53

Datuak

-0.53

])/

-0.53

POSITIVE LOGITS

bootstrapcdn

0.77

 appunto

0.76

verwijspagina

0.71

ViewFeatures

0.70

 AssemblyCulture

0.68

 whatever

0.61

henswürdigkeiten

0.60

ContentLoaded

0.57

oh

0.56

oh

0.56

Activations Density 0.251%

conversational or narrative elements related to knowledge or stating facts

No Comments

No Known Activations