INDEX

Explanations

terms related to racial identity and classification

oai_token-act-pair · gpt-3.5-turbo

terms related to race and ethnicity

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

 Dolphin

-0.70

 omission

-0.70

 Painter

-0.70

ĸļ

-0.69

 Rabbit

-0.69

Pub

-0.65

 Isles

-0.65

ABE

-0.65

 IMAGES

-0.65

 Carnival

-0.64

POSITIVE LOGITS

onder

0.86

GHz

0.85

ound

0.83

ield

0.83

atri

0.83

llular

0.82

imensional

0.82

atures

0.82

rop

0.80

ucle

0.79

Activations Density 0.072%

terms related to racial identity and classification

terms related to race and ethnicity

No Comments

No Known Activations