INDEX

Explanations

numerical values related to time, particularly the number 72

oai_token-act-pair · gpt-3.5-turbo

numerical values, particularly related to measurements or counts

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

yang

-0.87

BOOK

-0.86

gets

-0.70

eering

-0.69

achu

-0.69

feature

-0.69

furt

-0.68

fan

-0.67

lace

-0.67

ezvous

-0.67

POSITIVE LOGITS

 ILCS

0.94

0.82

icum

0.82

0.81

ipop

0.81

icably

0.81

ITY

0.75

velength

0.75

ocally

0.74

Activations Density 0.034%

numerical values related to time, particularly the number 72

numerical values, particularly related to measurements or counts

No Comments

No Known Activations