INDEX

Explanations

references to locations and events in a narrative context

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.03

1:0.05

2:0.05

3:0.12

4:0.10

5:0.07

6:0.02

7:0.09

8:0.04

9:0.03

10:0.11

11:0.25

Negative Logits

().

-3.31

"_

-3.29

"#

-3.20

="/

-2.99

":"/

-2.98

"/

-2.96

("

-2.92

soDeliveryDate

-2.87

}:

-2.85

>.

-2.83

POSITIVE LOGITS

!'

2.98

 Pict

2.71

↵

2.67

 slumped

2.58

 Whilst

2.57

 pictured

2.46

,'

2.43

↵↵

2.39

\'

2.32

2.27

Activations Density 0.045%

references to locations and events in a narrative context

No Known Activations