INDEX

Explanations

reasons and justifications for actions and beliefs

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

aarrggbb

-0.77

 للمعارف

-0.76

ContentAsync

-0.75

findpost

-0.75

rungsseite

-0.69

__(/*!

-0.69

 ſtate

-0.69

 ſtill

-0.68

 Monfieur

-0.68

thâu

-0.67

POSITIVE LOGITS

 because

0.64

 porque

0.57

Porque

0.54

because

0.54

 Porque

0.52

Because

0.52

 BECAUSE

0.52

 want

0.51

 weil

0.51

Parce

0.51

Activations Density 0.356%

reasons and justifications for actions and beliefs

No Comments

No Known Activations