INDEX

Explanations

references to splitting or dividing datasets and images into smaller parts or segments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Atkins

-0.58

nthesis

-0.48

leč

-0.47

tioners

-0.47

fır

-0.44

罄

-0.44

ecore

-0.44

жар

-0.43

ghold

-0.43

ferous

-0.42

POSITIVE LOGITS

 splits

1.23

 split

1.18

 divides

1.09

 Split

1.09

 splitting

1.08

Split

1.06

 partitioned

1.05

 Partition

1.05

 partition

1.03

splitter

1.03

Activations Density 0.433%

references to splitting or dividing datasets and images into smaller parts or segments

No Comments

No Known Activations