INDEX

Explanations

phrases related to cold weather or anesthesia

oai_token-act-pair · gpt-3.5-turbo

terms related to frost and freezing conditions

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

selves

-0.68

terior

-0.66

ENTION

-0.66

 Indones

-0.64

gae

-0.64

alogue

-0.64

ention

-0.64

ulhu

-0.63

ister

-0.62

>>>>>>>>

-0.62

POSITIVE LOGITS

bite

1.29

flake

0.95

enstein

0.91

cream

0.84

 Frost

0.83

iness

0.83

fur

0.81

fall

0.81

burn

0.81

 frost

0.80

Activations Density 0.010%

phrases related to cold weather or anesthesia

terms related to frost and freezing conditions

No Comments

No Known Activations