INDEX

Explanations

Biblical references and religious phrases with the word "unto"

oai_token-act-pair · gpt-3.5-turbo

words and phrases that denote a formal or biblical discourse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enhagen

-0.91

ãĤ§

-0.88

zsche

-0.85

ãĤ¶

-0.76

WAR

-0.75

ipal

-0.74

GN

-0.70

Syn

-0.69

isu

-0.68

itar

-0.68

POSITIVE LOGITS

 Hath

0.95

 unto

0.95

 thou

0.87

 hath

0.85

oak

0.85

 thee

0.85

thy

0.81

 mine

0.77

selves

0.75

yea

0.73

Activations Density 0.020%

Biblical references and religious phrases with the word "unto"

words and phrases that denote a formal or biblical discourse

No Comments

No Known Activations