INDEX

Explanations

phrases indicating increasing quantity or intensity

oai_token-act-pair · gpt-3.5-turbo

conjunctions and phrases indicating a relationship of addition or comparison

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

ĳå£«

-0.73

RAW

-0.70

 Peaks

-0.65

ãĤ´ãĥ³

-0.65

 robber

-0.64

 Sparrow

-0.64

 Saud

-0.64

 Blaz

-0.63

 Bulgar

-0.63

 Cros

-0.62

POSITIVE LOGITS

vous

0.87

ificantly

0.86

angled

0.78

 than

0.77

than

0.76

efficient

0.76

acho

0.76

fficient

0.75

cientious

0.74

itably

0.74

Activations Density 0.141%

phrases indicating increasing quantity or intensity

conjunctions and phrases indicating a relationship of addition or comparison

No Comments

No Known Activations