INDEX

Explanations

phrases indicating non-standard or atypical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 italienne

-0.69

 imprimée

-0.69

 scattata

-0.61

 préféré

-0.61

 gjerne

-0.60

 literaria

-0.60

 picha

-0.60

avance

-0.59

 innamor

-0.58

brainly

-0.58

POSITIVE LOGITS

non

1.18

NON

1.17

Non

1.16

Non

1.04

non

1.02

非

1.01

 Nong

0.95

NON

0.94

 nons

0.94

 Nons

0.91

Activations Density 0.096%

phrases indicating non-standard or atypical conditions

No Comments

No Known Activations