INDEX

Explanations

mentions of "sin" and related terms associated with wrongdoing or immorality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

]--;

-1.03

,:);

-0.94

 Parcelable

-0.93

 nakalista

-0.92

Geplaatst

-0.92

 myſelf

-0.91

 himſelf

-0.91

 Walkover

-0.90

 engraçadas

-0.88

]]

-0.88

POSITIVE LOGITS

sin

2.13

Sin

1.97

sin

1.91

Sin

1.84

SIN

1.73

 sins

1.63

SIN

1.49

 Sins

1.30

 sinful

1.22

 sinned

1.21

Activations Density 0.081%

mentions of "sin" and related terms associated with wrongdoing or immorality

No Comments

No Known Activations