INDEX

Explanations

mathematical expressions and symbols, particularly those involving single quotes and curly braces

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

 getLayout

-0.75

mentos

-0.68

انجليز

-0.68

 Duda

-0.68

 Mait

-0.66

KURZBESCHREIBUNG

-0.66

atott

-0.66

staun

-0.65

 ThemeData

-0.65

 immemorial

-0.64

POSITIVE LOGITS

1.11

+'

1.00

>'

0.99

}'

0.96

)’

0.94

′

0.92

=='

0.92

)'

0.91

:'

0.91

?'

0.91

Activations Density 0.189%

mathematical expressions and symbols, particularly those involving single quotes and curly braces

No Comments

No Known Activations