INDEX

Explanations

phrases and constructs that indicate repetition or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 propOrder

-0.79

 AssemblyTitle

-0.78

="@+

-0.66

 obicei

-0.63

énéral

-0.59

}$

-0.56

 initComponents

-0.56

 ↓,

-0.53

مصادر

-0.53

 Tana

-0.53

POSITIVE LOGITS

 BorderSide

0.66

 تضيفلها

0.60

 itself

0.56

saraba

0.56

ItemLayout

0.53

itself

0.53

これも

0.53

今年も

0.51

最後まで

0.50

ainville

0.49

Activations Density 0.308%

phrases and constructs that indicate repetition or emphasis

No Comments

No Known Activations