INDEX

Explanations

specific entities or nouns related to legal, political, or government contexts

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.06

1:0.03

2:0.10

3:0.15

4:0.04

5:0.11

6:0.07

7:0.05

8:0.09

9:0.10

10:0.10

11:0.05

Negative Logits

utics

-1.08

 Month

-1.05

cit

-1.01

ilaterally

-1.00

itored

-0.99

aea

-0.99

cigarettes

-0.99

Ear

-0.99

abetes

-0.98

galitarian

-0.97

POSITIVE LOGITS

 implication

1.19

 portion

1.14

 latter

1.09

iest

1.05

 equivalent

1.02

 moniker

1.01

 patriarch

1.00

mentioned

0.99

 antidote

0.98

ultimate

0.96

Activations Density 0.388%

specific entities or nouns related to legal, political, or government contexts

No Known Activations