INDEX

Explanations

expressions and references to knowledge, learning, and inquiry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 greateſt

-0.69

phus

-0.67

sterious

-0.65

moiselle

-0.65

 Sigue

-0.63

AndEndTag

-0.63

odorante

-0.62

pédie

-0.62

 contextLoads

-0.61

 headless

-0.61

POSITIVE LOGITS

солю

0.52

 completely

0.51

AddTagHelper

0.49

matchCondition

0.46

 like

0.45

us

0.45

MENAFN

0.45

 really

0.45

Hozzáférés

0.44

ScopeManager

0.44

Activations Density 0.310%

expressions and references to knowledge, learning, and inquiry

No Comments

No Known Activations