INDEX

Explanations

instances of foreign terms or names and their meanings

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

1:0.01

2:0.03

3:0.22

4:0.03

5:0.21

6:0.04

7:0.03

8:0.14

9:0.05

10:0.06

11:0.06

Negative Logits

 eyewitness

-2.18

 antim

-2.16

 legalized

-2.15

 biotech

-2.12

 embry

-2.08

 vaccines

-2.06

 Egyptians

-2.06

 insiders

-2.02

 civilizations

-2.01

 indo

-1.99

POSITIVE LOGITS

コ

3.04

ーティ

2.85

uton

2.76

ん

2.71

ン

2.70

utor

2.68

uto

2.68

isu

2.66

iku

2.62

 Takeru

2.60

Activations Density 0.023%

instances of foreign terms or names and their meanings

No Comments

No Known Activations