INDEX

Explanations

mentions of academic degrees

oai_token-act-pair · gpt-3.5-turbo

references to academic degrees and their significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

sels

-0.77

 Sioux

-0.69

ulative

-0.65

miah

-0.64

wolf

-0.64

 Bans

-0.63

gotten

-0.62

Tsu

-0.62

ded

-0.61

geist

-0.60

POSITIVE LOGITS

 degree

1.14

 degrees

1.03

 Degree

1.00

degree

0.98

uates

0.92

 Celsius

0.85

ploma

0.81

 Fahrenheit

0.74

Deg

0.73

MPH

0.73

Activations Density 0.007%

mentions of academic degrees

references to academic degrees and their significance

No Comments

No Known Activations