INDEX

Explanations

instances of being impacted or impressed by significant observations or experiences

New Auto-Interp

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.02

1:0.01

2:0.05

3:0.09

4:0.12

5:0.01

6:0.07

7:0.38

8:0.03

9:0.04

10:0.05

11:0.07

Negative Logits

soDeliveryDate

-1.76

 subsistence

-1.57

emer

-1.56

 indefinitely

-1.55

entary

-1.54

 conduit

-1.43

emate

-1.42

 emergencies

-1.41

 frontline

-1.41

 watchdog

-1.40

POSITIVE LOGITS

 similarities

1.93

 similarity

1.74

 resemblance

1.73

 Doodle

1.72

 Finding

1.70

 resemb

1.70

cookie

1.59

��

1.57

 Paint

1.56

 Subtle

1.56

Activations Density 0.002%

instances of being impacted or impressed by significant observations or experiences

No Known Activations