INDEX

Explanations

quantitative measures of performance and rankings across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

SequentialGroup

-0.78

tvguidetime

-0.63

colgroup

-0.59

AnchorStyles

-0.58

CloseOperation

-0.56

[]:

-0.55

WebVitals

-0.55

SceneManagement

-0.55

 مشين

-0.54

ंदीखरीदारी

-0.54

POSITIVE LOGITS

most

0.65

 most

0.61

 absoluto

0.59

 among

0.58

 berta

0.54

 עלי

0.54

 darin

0.54

LEADING

0.53

𝟲

0.53

 Most

0.52

Activations Density 0.181%

quantitative measures of performance and rankings across various contexts

No Comments

No Known Activations