INDEX

Explanations

phrases that indicate statistics or numerical data related to topics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.02

2:0.17

3:0.12

4:0.19

5:0.08

6:0.03

7:0.03

8:0.03

9:0.14

10:0.06

11:0.02

Negative Logits

STAR

-1.44

Planet

-1.24

Pred

-1.24

 hint

-1.21

TION

-1.21

Dub

-1.19

 Balt

-1.15

ンジ

-1.15

otes

-1.14

 Sloan

-1.13

POSITIVE LOGITS

 laun

1.34

 probation

1.26

 increments

1.25

 reckoning

1.22

 elapsed

1.22

Duration

1.21

 mortar

1.19

oulos

1.17

uana

1.17

inement

1.15

Activations Density 0.029%

phrases that indicate statistics or numerical data related to topics

No Comments

No Known Activations