INDEX

Explanations

references to religious figures, particularly pastors

oai_token-act-pair · gpt-3.5-turbo

references to individuals with the title "pastor."

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

urat

-0.83

plets

-0.69

axy

-0.65

EMS

-0.65

thin

-0.64

 Carbuncle

-0.62

Ø§ÙĦ

-0.62

xp

-0.60

ibaba

-0.60

 Petroleum

-0.60

POSITIVE LOGITS

 pastor

0.99

 Pastor

0.93

esses

0.88

 preached

0.87

iffe

0.81

 preach

0.80

angel

0.79

ess

0.78

 evangel

0.76

angelo

0.76

Activations Density 0.021%

references to religious figures, particularly pastors

references to individuals with the title "pastor."

No Comments

No Known Activations