INDEX

Explanations

references to individuals and their medical or legal claims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 intptr

-0.51

 insuffisamment

-0.46

sweep

-0.46

ilité

-0.46

 gustaría

-0.44

ban

-0.44

励

-0.44

style

-0.43

bieron

-0.43

 ajudam

-0.43

POSITIVE LOGITS

Rhestr

0.69

kloped

0.67

 समीक्षाओं

0.63

 SwitchCompat

0.59

EndContext

0.59

 ujednoznacz

0.58

MENAFN

0.58

ėd

0.57

UnusedPrivate

0.57

windowFixed

0.57

Activations Density 0.589%

references to individuals and their medical or legal claims

No Comments

No Known Activations