INDEX

Explanations

gender-related words and workplace terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

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

 Buster

-0.65

vich

-0.65

 Warwick

-0.64

 Everything

-0.62

 Corpus

-0.61

Byr

-0.61

 Sandwich

-0.60

 Lavrov

-0.60

RAW

-0.60

forcer

-0.59

POSITIVE LOGITS

 clustered

0.80

 perished

0.80

 individually

0.77

 outright

0.76

eligible

0.75

 either

0.74

ebted

0.71

 voluntarily

0.70

 classified

0.70

 surveyed

0.70

Activations Density 3.952%

gender-related words and workplace terms

No Comments

No Known Activations