INDEX

Explanations

narrative elements and structural markers in written content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Roskov

-0.92

XmlAccessType

-0.87

uxxxx

-0.85

 '\\;'

-0.83

 MenuView

-0.81

 ویکی‌پدی

-0.81

SharedDtor

-0.75

InjectAttribute

-0.74

bootstrapcdn

-0.69

MIDDLEWARE

-0.68

POSITIVE LOGITS

 mutagen

0.53

حم

0.52

 epist

0.49

 levy

0.49

Tracks

0.48

ɛ

0.48

 amethyst

0.47

 communication

0.47

soever

0.47

 Amethyst

0.47

Activations Density 0.021%

narrative elements and structural markers in written content

No Comments

No Known Activations