INDEX

Explanations

references to returning or going back

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

:✨

-0.84

 Larsen

-0.82

 Larson

-0.80

λία

-0.80

%)$

-0.78

CMA

-0.77

ряда

-0.73

°•

-0.73

MeasureSpec

-0.73

 Goya

-0.72

POSITIVE LOGITS

 back

1.83

back

1.76

 Back

1.74

Back

1.74

BACK

1.68

 BACK

1.65

 backs

1.35

backs

1.25

 zurück

1.20

 indietro

1.18

Activations Density 0.052%

references to returning or going back

No Comments

No Known Activations