INDEX

Explanations

modal verbs indicating possibility or uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.03

1:0.03

2:0.06

3:0.05

4:0.07

5:0.41

6:0.02

7:0.04

8:0.02

9:0.15

10:0.03

11:0.04

Negative Logits

 until

-3.76

 till

-3.60

til

-3.03

 except

-2.94

 while

-2.94

 uninterrupted

-2.87

 before

-2.64

 continues

-2.64

 without

-2.63

 stays

-2.62

POSITIVE LOGITS

moil

3.08

annot

3.08

将

2.64

 Cannot

2.63

\":

2.61

Not

2.53

 Must

2.52

Can

2.49

 Wrong

2.49

Yes

2.47

Activations Density 0.049%

modal verbs indicating possibility or uncertainty

No Comments

No Known Activations