INDEX

Explanations

terms that express certainty or emphasis in a statement

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

phrases and terms related to discrimination or prejudice against particular groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-att-kk

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

0:0.06

1:0.03

2:0.18

3:0.07

4:0.06

5:0.10

6:0.03

7:0.02

8:0.10

9:0.24

10:0.04

11:0.03

Negative Logits

amins

-1.50

Jr

-1.32

Mich

-1.30

ゼウス

-1.29

inar

-1.25

Fra

-1.25

usercontent

-1.24

 Bett

-1.23

Calif

-1.22

 resil

-1.21

POSITIVE LOGITS

 clauses

1.34

 binding

1.30

 revised

1.29

 memor

1.27

 borrowing

1.22

 derivatives

1.21

iths

1.16

 transfer

1.15

 ticking

1.14

 merged

1.13

Activations Density 0.006%

terms that express certainty or emphasis in a statement

phrases and terms related to discrimination or prejudice against particular groups

No Comments

No Known Activations