INDEX

Explanations

references to God and divine concepts within 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-0.94

 themſelves

-0.91

 poffe

-0.90

 itſelf

-0.89

 pleaſure

-0.89

]";

-0.86

 fhew

-0.84

 ſee

-0.83

 resent

-0.83

 houſe

-0.82

POSITIVE LOGITS

God

2.11

God

1.96

GOD

1.79

god

1.74

god

1.72

GOD

1.61

 Dios

1.43

 Gods

1.32

 gods

1.28

Gods

1.27

Activations Density 0.023%

references to God and divine concepts within the text

No Comments

No Known Activations