INDEX

Explanations

proper nouns, specifically 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

0:0.01

1:0.04

2:0.11

3:0.25

4:0.01

5:0.02

6:0.09

7:0.07

8:0.05

9:0.13

10:0.07

11:0.08

Negative Logits

kefeller

-1.21

 contrace

-1.09

 Rangers

-1.06

 Tactics

-1.04

 Rampage

-1.04

draw

-1.03

offensive

-1.02

texture

-1.02

 lightsaber

-1.02

bley

-1.01

POSITIVE LOGITS

sein

1.31

ammed

1.22

llah

1.22

 Lama

1.21

schild

1.20

hya

1.18

lia

1.17

�

1.16

HAM

1.15

asher

1.14

Activations Density 0.001%

proper nouns, specifically names and places

No Comments

No Known Activations