INDEX

Explanations

instances of the word "was" and its contextual variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

endphp

-0.86

 nahilalakip

-0.75

+#+#

-0.73

SharedDtor

-0.73

SourceChecksum

-0.72

клопе

-0.71

-0.66

INCREF

-0.65

ГЛА

-0.65

ніципа

-0.65

POSITIVE LOGITS

 pernah

0.69

 sempat

0.67

 previously

0.66

previously

0.64

Previously

0.64

 Previously

0.63

เคย

0.61

originally

0.61

 erst

0.61

 originally

0.61

Activations Density 0.640%

instances of the word "was" and its contextual variations

No Comments

No Known Activations