INDEX

Explanations

phrases that indicate actions or accusations related to individuals or groups

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_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

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.03

2:0.07

3:0.07

4:0.02

5:0.03

6:0.05

7:0.05

8:0.06

9:0.27

10:0.12

11:0.17

Negative Logits

Comments

-1.30

Pokémon

-1.26

Size

-1.25

 greets

-1.21

Discussion

-1.21

FILE

-1.16

 unfolds

-1.15

ISE

-1.14

Ball

-1.14

oku

-1.14

POSITIVE LOGITS

 wounding

1.48

 distortion

1.35

 cannibal

1.34

grave

1.30

 sabot

1.30

 killing

1.30

gou

1.26

VAT

1.25

 distortions

1.18

 inflicting

1.17

Activations Density 0.011%

phrases that indicate actions or accusations related to individuals or groups

No Comments

No Known Activations