INDEX

Explanations

terms related to negative aspects or drawbacks

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

2:0.05

3:0.09

4:0.03

5:0.05

6:0.06

7:0.12

8:0.07

9:0.11

10:0.07

11:0.25

Negative Logits

vironment

-1.31

REF

-1.31

ouston

-1.24

iverse

-1.22

itored

-1.22

combe

-1.22

eday

-1.21

dayName

-1.19

lished

-1.18

burgh

-1.17

POSITIVE LOGITS

 cumbers

1.42

 brut

1.36

 downside

1.30

 drawback

1.26

 disadvantages

1.25

 Warfare

1.24

 excess

1.22

isks

1.18

 decreases

1.17

 gimm

1.17

Activations Density 0.004%

terms related to negative aspects or drawbacks

No Comments

No Known Activations