INDEX

Explanations

references to specific names and terms associated with people or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 <<<<<<<<<<<<<<

-1.13

 autorytatywna

-1.10

تقاوى

-0.96

 Paglinawan

-0.91

MigrationBuilder

-0.91

+#+#

-0.91

Personensuche

-0.90

 pinulongan

-0.89

tagext

-0.89

\{\\

-0.88

POSITIVE LOGITS

zzz

0.97

zzzz

0.89

Baz

0.79

zy

0.78

Kuz

0.77

ZZZZ

0.75

rz

0.74

zar

0.73

zz

0.73

iz

0.73

Activations Density 0.216%

references to specific names and terms associated with people or entities

No Comments

No Known Activations