INDEX

Explanations

phrases indicating experimental results or outcomes in scientific studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

fromnode

-0.66

 ویکی‌پدیا

-0.61

ARCHIVE

-0.60

 obligé

-0.59

 tentatively

-0.59

ecture

-0.59

)$/,

-0.58

IVITY

-0.58

 depressive

-0.58

)':

-0.58

POSITIVE LOGITS

 results

1.19

results

0.94

 effects

0.87

 مشين

0.84

 Results

0.76

 means

0.76

 impacts

0.72

 needs

0.68

Results

0.63

 depends

0.63

Activations Density 0.267%

phrases indicating experimental results or outcomes in scientific studies

No Comments

No Known Activations