INDEX

Explanations

phrases that present contrasting options or scenarios

oai_token-act-pair · gpt-3.5-turbo

discussions around contentious issues and uncertainties surrounding them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Ĥª

-0.73

©¶æ¥µ

-0.67

.).

-0.64

%.

-0.64

 Lastly

-0.64

almost

-0.63

ļéĨĴ

-0.63

ŃĶ

-0.62

.''.

-0.59

é¾įå¥ĳå£«

-0.56

POSITIVE LOGITS

or

1.55

nor

1.40

OR

1.01

Or

0.99

Or

0.93

 whatsoever

0.70

Either

0.65

or

0.65

 Either

0.65

 either

0.65

Activations Density 0.430%

phrases that present contrasting options or scenarios

discussions around contentious issues and uncertainties surrounding them

No Comments

No Known Activations