INDEX

Explanations

occurrences of specific letters or letter combinations in the text

New Auto-Interp

Top Features by Cosine Similarity

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

0:0.03

1:0.01

2:0.05

3:0.06

4:0.04

5:0.04

6:0.46

7:0.05

8:0.03

9:0.06

10:0.06

11:0.05

Negative Logits

EStreamFrame

-1.52

 heel

-1.28

��

-1.28

pport

-1.25

�

-1.24

POV

-1.23

ャ

-1.23

hole

-1.21

rency

-1.21

inki

-1.21

POSITIVE LOGITS

fell

1.18

irie

1.15

 contrasts

1.13

 Bezos

1.10

 prepar

1.10

��

1.09

catentry

1.09

 Sounds

1.05

Wol

1.04

Activations Density 0.001%

occurrences of specific letters or letter combinations in the text

No Known Activations