INDEX

Explanations

proper nouns, particularly names and places

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

0:0.08

1:0.06

2:0.11

3:0.03

4:0.05

5:0.03

6:0.08

7:0.15

8:0.14

9:0.04

10:0.08

11:0.10

Negative Logits

Zup

-1.21

etheless

-1.21

¶

-1.18

enegger

-1.11

.–

-1.10

terness

-1.09

naire

-1.08

rawdownloadcloneembedreportprint

-1.07

 ********************************

-1.06

Reviewer

-1.05

POSITIVE LOGITS

perate

1.25

 shores

1.21

 destinations

1.17

 coffers

1.14

 purposes

1.12

inia

1.11

future

1.11

gate

1.02

 Harbor

1.02

 embassies

1.01

Activations Density 0.169%

proper nouns, particularly names and places

No Comments

No Known Activations