INDEX

Explanations

technical terms related to hardware and development kits

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

0:0.07

1:0.03

2:0.26

3:0.05

4:0.14

5:0.06

6:0.03

7:0.03

8:0.05

9:0.13

10:0.06

11:0.02

Negative Logits

��

-1.40

��

-1.30

aceae

-1.24

én

-1.22

 Russ

-1.12

 quint

-1.12

 favourable

-1.08

teness

-1.08

Merit

-1.08

 Categories

-1.07

POSITIVE LOGITS

eanor

1.24

hent

1.17

utsche

1.09

exempt

1.08

Notice

1.04

ounge

1.04

Hub

1.04

 Detail

1.04

auga

1.02

irect

1.02

Activations Density 0.008%

technical terms related to hardware and development kits

No Comments

No Known Activations