INDEX

Explanations

terms related to legal processes and health research

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

 esetén

-0.64

férences

-0.54

 nélkül

-0.53

níci

-0.52

 Qualquer

-0.52

âteau

-0.51

Kjelder

-0.50

 Sira

-0.50

 Caron

-0.50

ító

-0.50

POSITIVE LOGITS

providedIn

0.76

Portail

0.62

 ComVisible

0.58

aarrggbb

0.57

 SPDX

0.56

CppMethod

0.55

__(/*!

0.54

 المعيارى

0.54

########.

0.53

pédie

0.53

Activations Density 1.904%

terms related to legal processes and health research

No Comments

No Known Activations