INDEX

Explanations

phrases indicating similarity or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

onso

-0.56

es

-0.56

!("{

-0.52

 Nase

-0.50

 Græ

-0.50

lección

-0.50

arbox

-0.50

 ulang

-0.49

といけない

-0.49

assigns

-0.49

POSITIVE LOGITS

 nahilalakip

1.07

 similar

1.06

 SIMILAR

1.04

RectangleBorder

1.02

Similar

1.01

 Similar

1.01

similar

1.00

Похо

0.97

iliar

0.92

 simil

0.92

Activations Density 0.175%

phrases indicating similarity or comparisons

No Comments

No Known Activations