INDEX

Explanations

phrases indicating quantity or enumeration

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

ContextHolder

-0.64

ですか

-0.63

icho

-0.63

verhältnisse

-0.63

 prez

-0.63

 fusca

-0.60

 Vorbild

-0.59

 Schae

-0.59

 houſe

-0.58

 walls

-0.58

POSITIVE LOGITS

 ряд

1.20

 several

1.14

 ряда

1.07

several

1.07

 Plusieurs

1.00

 تضيفلها

0.98

 numerous

0.97

いくつかの

0.96

いくつか

0.95

 various

0.94

Activations Density 0.168%

phrases indicating quantity or enumeration

No Comments

No Known Activations