INDEX

Explanations

numbers and identifiers in the dataset

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 surla

-1.06

 pinulongan

-0.97

Билгалдахарш

-0.87

HasForeignKey

-0.86

脚注の使い方

-0.80

KURZBESCHREIBUNG

-0.80

ConstraintMaker

-0.79

الدراسه

-0.77

ChildScrollView

-0.76

 nahilalakip

-0.76

POSITIVE LOGITS

 pstmt

0.54

mathrm

0.52

 Majefty

0.48

󠁢

0.47

ulemon

0.47

 pngtree

0.44

 pageNo

0.44

’

0.43

ándola

0.43

toHaveBeenCalled

0.43

Activations Density 0.883%

numbers and identifiers in the dataset

No Comments

No Known Activations