INDEX

Explanations

conjunctions and articles used in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

miyorum

-0.74

Palmarès

-0.61

"]));

-0.59

 marinho

-0.56

 departamentos

-0.55

 utafitiHapana

-0.55

 humanas

-0.54

pení

-0.54

脚注の使い方

-0.53

']));

-0.53

POSITIVE LOGITS

0.66

 plenty

0.64

 high

0.61

an

0.58

 lots

0.58

 wide

0.57

PreferredItem

0.56

 good

0.56

kháu

0.54

plenty

0.53

Activations Density 0.567%

conjunctions and articles used in the text

No Comments

No Known Activations