INDEX

Explanations

expressions of gratitude

oai_token-act-pair · gpt-3.5-turbo

phrases expressing gratitude or thanks

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

edin

-0.96

soDeliveryDate

-0.88

é¾

-0.87

LAB

-0.87

orbit

-0.79

quickShipAvailable

-0.79

Myth

-0.79

archy

-0.79

Ops

-0.78

arc

-0.77

POSITIVE LOGITS

 example

0.84

 bravery

0.78

 pity

0.78

 awhile

0.78

 subscribing

0.77

gery

0.76

 recognizing

0.76

geries

0.74

 goodness

0.74

 electing

0.74

Activations Density 0.054%

expressions of gratitude

phrases expressing gratitude or thanks

No Comments

No Known Activations