INDEX

Explanations

references to services and villages in 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 @ 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

fjspx

-0.81

 Argonne

-0.79

 auffi

-0.79

 transfieras

-0.79

AutoresizingMask

-0.78

 Seeder

-0.75

 мәкал

-0.74

Obrázky

-0.74

 purpoſe

-0.74

èdia

-0.74

POSITIVE LOGITS

ther

0.74

↵↵

0.63

The

0.60

<eos>

0.59

The

0.55

↵

0.53

“

0.52

↵↵↵

0.50

Mr

0.48

0.47

Activations Density 0.086%

references to services and villages in various contexts

No Comments

No Known Activations