INDEX

Explanations

numerical values ending in '72'

oai_token-act-pair · gpt-3.5-turbo

references to the number 72 and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

yang

-0.84

achu

-0.81

BOOK

-0.77

gregation

-0.69

furt

-0.69

gets

-0.68

fan

-0.68

lÃ©

-0.67

lace

-0.67

eering

-0.66

POSITIVE LOGITS

 ILCS

0.87

ipop

0.84

ITY

0.82

0.81

0.76

ITIES

0.76

icum

0.76

0.73

elsius

0.73

Activations Density 0.042%

numerical values ending in '72'

references to the number 72 and its variations

No Comments

No Known Activations