INDEX

Explanations

references to small or limited quantities

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

umab

-0.52

Thunk

-0.48

äne

-0.46

+#+

-0.45

var

-0.43

 Orozco

-0.43

icali

-0.42

ñata

-0.42

 gefähr

-0.41

‌ش

-0.41

POSITIVE LOGITS

 small

1.18

small

1.12

Small

1.07

 kecil

1.07

 Small

1.00

 pequeño

0.99

 SMALL

0.99

 tiny

0.99

 pequeña

0.98

 کوچک

0.95

Activations Density 0.610%

references to small or limited quantities

No Comments

No Known Activations