INDEX

Explanations

references to monetary values or statistics

oai_token-act-pair · gpt-3.5-turbo

monetary values and financial statistics

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

ande

-0.48

laws

-0.48

acas

-0.48

Reviewer

-0.47

 Collider

-0.47

evin

-0.46

bris

-0.45

mates

-0.44

íķ

-0.42

pse

-0.42

POSITIVE LOGITS

 percent

0.76

 apiece

0.73

0.71

0.67

 million

0.66

million

0.64

 thousand

0.64

%%

0.63

0.62

 cubic

0.62

Activations Density 0.612%

references to monetary values or statistics

monetary values and financial statistics

No Comments

No Known Activations