INDEX

Explanations

phrases related to cause and effect

oai_token-act-pair · gpt-3.5-turbo

phrases indicating consequences or results

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

pload

-0.66

anship

-0.64

kers

-0.62

chio

-0.62

intend

-0.62

tera

-0.61

kered

-0.60

Caf

-0.59

IPS

-0.59

afort

-0.59

POSITIVE LOGITS

 thereof

1.02

ainer

0.78

of

0.74

iveness

0.69

 stemming

0.65

ively

0.63

growth

0.62

raction

0.62

bringer

0.60

)=(

0.59

Activations Density 0.028%

phrases related to cause and effect

phrases indicating consequences or results

No Comments

No Known Activations