INDEX

Explanations

references to or mentions of the Vatican

oai_token-act-pair · gpt-3.5-turbo

references to the Vatican and its related entities

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

lasses

-0.81

ãģ¦

-0.81

pring

-0.80

awks

-0.79

served

-0.76

eworld

-0.76

Haw

-0.75

mental

-0.75

haw

-0.73

nesota

-0.73

POSITIVE LOGITS

arium

0.89

 Vatican

0.89

Leaks

0.86

 Embassy

0.82

 Patriarch

0.80

 bureaucracy

0.80

 pope

0.77

 brass

0.77

itary

0.76

 decre

0.75

Activations Density 0.009%

references to or mentions of the Vatican

references to the Vatican and its related entities

No Comments

No Known Activations