INDEX

Explanations

names or terms related to financial or investment activities

oai_token-act-pair · gpt-3.5-turbo 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

0:0.08

1:0.02

2:0.34

3:0.06

4:0.15

5:0.05

6:0.02

7:0.02

8:0.07

9:0.07

10:0.05

11:0.02

Negative Logits

��

-1.49

catentry

-1.35

-+-+

-1.35

 unden

-1.34

 millenn

-1.33

 pregn

-1.31

ワン

-1.28

 srfAttach

-1.25

 adolesc

-1.25

ASED

-1.24

POSITIVE LOGITS

 Santos

1.45

rences

1.41

andestine

1.41

gue

1.36

ubric

1.31

ño

1.30

vous

1.29

heed

1.25

aiden

1.24

tics

1.24

Activations Density 0.008%

names or terms related to financial or investment activities

No Comments

No Known Activations