INDEX

Explanations

elements related to image metadata and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 незавершена

-0.44

########.

-0.43

 gynhyrchwyd

-0.43

AndEndTag

-0.42

нодоро

-0.42

 modelAndView

-0.41

ági

-0.40

 Einbau

-0.40

chero

-0.40

 Converting

-0.40

POSITIVE LOGITS

CrossRef

0.36

rel

0.36

のは

0.35

이션

0.35

 pinulongan

0.35

 Archipelago

0.35

Дереккөздер

0.35

clearly

0.34

 SECT

0.34

CreateIndex

0.34

Activations Density 0.183%

elements related to image metadata and identifiers

No Comments

No Known Activations