INDEX

Explanations

references to specific religious groups, particularly Orthodox

oai_token-act-pair · gpt-3.5-turbo

instances of the term "Orthodox" in various contexts related to Orthodox Judaism and Christianity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ptives

-0.90

ptoms

-0.89

nels

-0.82

arcity

-0.78

stract

-0.77

************

-0.76

rill

-0.73

uncle

-0.70

aneously

-0.70

enance

-0.70

POSITIVE LOGITS

omy

0.90

 rabb

0.84

osate

0.83

thodox

0.80

onite

0.80

 Patriarch

0.79

 fundamental

0.78

 Judaism

0.77

 orthodox

0.76

Activations Density 0.016%

references to specific religious groups, particularly Orthodox

instances of the term "Orthodox" in various contexts related to Orthodox Judaism and Christianity

No Comments

No Known Activations