INDEX

Explanations

information related to relationships, marriage, divorce, family dynamics, gender roles, and societal issues

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

comparisons related to gender dynamics in relationships and marital status

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

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

 hawk

-0.67

 prope

-0.67

planet

-0.67

 plead

-0.66

 Centauri

-0.65

jriwal

-0.64

 hurry

-0.63

agy

-0.63

liner

-0.63

 pleading

-0.62

POSITIVE LOGITS

 Researchers

1.25

 psychologists

1.25

 longitudinal

1.24

 Psychology

1.19

Researchers

1.17

Study

1.15

 researchers

1.13

 Gallup

1.13

 Study

1.12

 psychologist

1.12

Activations Density 0.399%

information related to relationships, marriage, divorce, family dynamics, gender roles, and societal issues

comparisons related to gender dynamics in relationships and marital status

No Comments

No Known Activations