INDEX

Explanations

words related to actions involving closing, shutting, or tracking down

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Hochspringen

-0.68

الحياه

-0.57

orianCalendar

-0.51

arcas

-0.50

culoskeletal

-0.50

Hauptartikel

-0.50

herzog

-0.49

tentu

-0.48

kelijk

-0.47

jalá

-0.47

POSITIVE LOGITS

 down

4.16

down

3.34

Down

3.13

 Down

3.01

 DOWN

2.93

DOWN

2.70

downs

2.36

 downs

2.19

ダウン

2.13

dow

1.92

Activations Density 0.817%

words related to actions involving closing, shutting, or tracking down

No Comments

No Known Activations