INDEX

Explanations

key names and important entities within a narrative context

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

1:0.14

2:0.10

3:0.03

4:0.01

5:0.04

6:0.09

7:0.06

8:0.26

9:0.03

10:0.11

11:0.06

Negative Logits

endi

-1.20

tch

-1.15

�

-1.14

arez

-1.13

plet

-1.12

obo

-1.12

acca

-1.12

minus

-1.11

agos

-1.11

otype

-1.03

POSITIVE LOGITS

 nonetheless

1.74

 nevertheless

1.40

 msec

1.28

 persists

1.24

 aren

1.19

etheless

1.18

 caution

1.17

 differs

1.17

isn

1.12

 cautioned

1.12

Activations Density 0.306%

key names and important entities within a narrative context

No Known Activations