INDEX

Explanations

references to pairs of distinct entities, particularly in relation to their interactions 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 @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ritage

-0.53

sproz

-0.51

icity

-0.51

byl

-0.50

clat

-0.49

 aload

-0.48

huang

-0.47

barco

-0.47

xtension

-0.47

 congel

-0.46

POSITIVE LOGITS

 elkaar

1.08

 einander

0.94

 birbir

0.93

GEBURTSDATUM

0.87

 mutually

0.87

 saling

0.84

feinander

0.83

 AssemblyCulture

0.83

 arasındaki

0.83

 together

0.82

Activations Density 0.834%

references to pairs of distinct entities, particularly in relation to their interactions or comparisons

No Comments

No Known Activations