INDEX

Explanations

terms related to architectural features and structures

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

 kesempatan

-0.42

sw

-0.42

ban

-0.41

stream

-0.40

persion

-0.40

ый

-0.39

ta

-0.39

POSITIVE LOGITS

 tower

1.46

 towers

1.45

 TOWER

1.37

 Tower

1.31

 Towers

1.29

Tower

1.25

tower

1.24

MemoryWarning

1.16

towers

1.15

 defaultstate

0.98

Activations Density 0.258%

terms related to architectural features and structures

No Comments

No Known Activations