INDEX

Explanations

proper nouns representing a specific person

oai_token-act-pair · gpt-3.5-turbo

references to a specific male individual in various contexts

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

iculty

-0.63

DAY

-0.61

Interest

-0.58

 affiliate

-0.58

reshold

-0.56

com

-0.56

terms

-0.56

 Articles

-0.56

 Jindal

-0.55

requisite

-0.55

POSITIVE LOGITS

zbollah

1.21

resy

1.04

'll

1.03

reditary

1.03

 Majesty

0.96

uristic

0.95

gemony

0.93

pherd

0.92

eded

0.91

aven

0.91

Activations Density 0.282%

proper nouns representing a specific person

references to a specific male individual in various contexts

No Comments

No Known Activations