INDEX

Explanations

expressions of concern or worry regarding social issues

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

0:0.02

1:0.05

2:0.05

3:0.04

4:0.02

5:0.05

6:0.04

7:0.08

8:0.08

9:0.08

10:0.07

11:0.35

Negative Logits

cellent

-1.30

alach

-1.27

 winner

-1.25

ARGET

-1.20

CLUS

-1.19

 sublime

-1.19

 concess

-1.18

 winners

-1.17

 Redemption

-1.16

CLUD

-1.16

POSITIVE LOGITS

 premature

1.37

 shortages

1.35

 sudden

1.33

izzard

1.28

 worsened

1.27

due

1.26

 trolls

1.24

 delays

1.24

 shortage

1.22

 Warn

1.21

Activations Density 0.099%

expressions of concern or worry regarding social issues

No Comments

No Known Activations