INDEX

Explanations

triggering and emphatic words, often in capital letters

oai_token-act-pair · gpt-3.5-turbo

negations and affirmations in statements

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

ipel

-0.73

adem

-0.71

ongyang

-0.70

ffen

-0.69

ãĥĥãĥĪ

-0.69

odore

-0.67

igration

-0.66

iasis

-0.65

atz

-0.64

iel

-0.63

POSITIVE LOGITS

THING

1.22

ELY

1.17

 THERE

1.05

 MUCH

1.02

NOT

1.01

VER

1.00

YOU

1.00

TING

0.99

INESS

0.99

ICE

0.99

Activations Density 0.112%

triggering and emphatic words, often in capital letters

negations and affirmations in statements

No Comments

No Known Activations