INDEX

Explanations

elements related to moral dilemmas or consequences

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

 disambiguazione

-0.58

SharedDtor

-0.55

pagestyle

-0.49

はじめに

-0.47

íritu

-0.47

 hår

-0.46

 prefeito

-0.46

новниш

-0.44

ArrowToggle

-0.44

khe

-0.44

POSITIVE LOGITS

Instead

0.85

 Instead

0.79

AutoScale

0.75

tdessen

0.73

 instead

0.71

awtextra

0.68

instead

0.66

vece

0.61

}{@

0.57

Anyway

0.56

Activations Density 0.347%

elements related to moral dilemmas or consequences

No Comments

No Known Activations