INDEX

Explanations

references to facial hair, particularly beards

oai_token-act-pair · gpt-3.5-turbo

words related to beards

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

ĸļ

-0.76

ĺħ

-0.67

ONSORED

-0.63

wei

-0.63

mington

-0.62

pheus

-0.61

gd

-0.60

 miscar

-0.59

 experien

-0.59

ydia

-0.58

POSITIVE LOGITS

hips

1.14

hip

1.07

ards

1.03

ystem

0.91

haw

0.91

nesses

0.87

hire

0.86

robe

0.84

ard

0.82

DragonMagazine

0.81

Activations Density 0.020%

references to facial hair, particularly beards

words related to beards

No Comments

No Known Activations